cjw/amd-r9700-ai-toolboxes
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity

more banchmarks

Browse Source
This commit is contained in:
Donato Capitella
2025-12-07 16:57:56 +00:00
parent 672487a72b
commit 99d8dbe914
433 changed files with 25533 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7-nightly-rocwmma__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 959.74 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 17.59 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7-nightly-rocwmma__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7-nightly-rocwmma] Ministral-3-14B-Instruct-2512-BF16__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7-nightly-rocwmma__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 305.03 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 17.59 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7-nightly-rocwmma__hblt0__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7-nightly-rocwmma] Ministral-3-14B-Instruct-2512-BF16__hblt0__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7-nightly__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 761.86 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 18.02 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7-nightly__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7-nightly] Ministral-3-14B-Instruct-2512-BF16__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7-nightly__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 280.13 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 18.01 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7-nightly__hblt0__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7-nightly] Ministral-3-14B-Instruct-2512-BF16__hblt0__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7.9-rocwmma__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 665.78 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 17.95 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7.9-rocwmma__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7.9-rocwmma] Ministral-3-14B-Instruct-2512-BF16__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7.9-rocwmma__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 262.83 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 17.95 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7.9-rocwmma__hblt0__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7.9-rocwmma] Ministral-3-14B-Instruct-2512-BF16__hblt0__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7.9__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 767.43 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 18.07 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7.9__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7.9] Ministral-3-14B-Instruct-2512-BF16__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7.9__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 275.13 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 18.07 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm-7.9__hblt0__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7.9] Ministral-3-14B-Instruct-2512-BF16__hblt0__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 688.43 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 17.97 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm6_4_4-rocwmma] Ministral-3-14B-Instruct-2512-BF16__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 271.52 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 17.98 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm6_4_4-rocwmma] Ministral-3-14B-Instruct-2512-BF16__hblt0__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 829.03 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 18.10 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm6_4_4] Ministral-3-14B-Instruct-2512-BF16__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 290.54 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 18.11 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm6_4_4__hblt0__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm6_4_4] Ministral-3-14B-Instruct-2512-BF16__hblt0__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 665.80 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 17.95 ± 0.00 |
build: 22577583a (7312)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm7.1.1-rocwmma] Ministral-3-14B-Instruct-2512-BF16__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 262.76 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 17.95 ± 0.00 |
build: 22577583a (7312)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm7.1.1-rocwmma] Ministral-3-14B-Instruct-2512-BF16__hblt0__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 766.84 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 18.09 ± 0.00 |
build: 22577583a (7312)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm7.1.1] Ministral-3-14B-Instruct-2512-BF16__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 274.75 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 18.07 ± 0.00 |
build: 22577583a (7312)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1__hblt0__fa1__longctx32768__single.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/Ministral-3-14B-Instruct-2512-BF16.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm7.1.1] Ministral-3-14B-Instruct-2512-BF16__hblt0__fa1 __longctx32768 failed (exit 0)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__vulkan_amdvlk__fa1__longctx16384__single.log
+12
View File
@@ -0,0 +1,12 @@
WARNING: radv is not a conformant Vulkan implementation, testing use only.
WARNING: radv is not a conformant Vulkan implementation, testing use only.
ggml_vulkan: Found 3 Vulkan devices:
ggml_vulkan: 0 = AMD Radeon AI PRO R9700 (AMD open-source driver) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
ggml_vulkan: 1 = AMD Radeon AI PRO R9700 (AMD open-source driver) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
ggml_vulkan: 2 = AMD Ryzen 9 9900X3D 12-Core Processor (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none
| model | size | params | backend | ngl | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | Vulkan | 99 | 1 | pp2048 @ d16384 | 310.96 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | Vulkan | 99 | 1 | tg32 @ d16384 | 13.87 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__vulkan_amdvlk__fa1__longctx32768__single.log
+12
View File
@@ -0,0 +1,12 @@
WARNING: radv is not a conformant Vulkan implementation, testing use only.
WARNING: radv is not a conformant Vulkan implementation, testing use only.
ggml_vulkan: Found 3 Vulkan devices:
ggml_vulkan: 0 = AMD Radeon AI PRO R9700 (AMD open-source driver) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
ggml_vulkan: 1 = AMD Radeon AI PRO R9700 (AMD open-source driver) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
ggml_vulkan: 2 = AMD Ryzen 9 9900X3D 12-Core Processor (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none
| model | size | params | backend | ngl | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | Vulkan | 99 | 1 | pp2048 @ d32768 | 194.73 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | Vulkan | 99 | 1 | tg32 @ d32768 | 10.53 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__vulkan_radv__fa1__longctx16384__single.log
+12
View File
@@ -0,0 +1,12 @@
WARNING: radv is not a conformant Vulkan implementation, testing use only.
WARNING: radv is not a conformant Vulkan implementation, testing use only.
ggml_vulkan: Found 3 Vulkan devices:
ggml_vulkan: 0 = AMD Ryzen 9 9900X3D 12-Core Processor (RADV RAPHAEL_MENDOCINO) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 65536 | int dot: 1 | matrix cores: none
ggml_vulkan: 1 = AMD Radeon AI PRO R9700 (RADV GFX1201) (radv) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
ggml_vulkan: 2 = AMD Radeon AI PRO R9700 (RADV GFX1201) (radv) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
| model | size | params | backend | ngl | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | Vulkan | 99 | 1 | pp2048 @ d16384 | 550.05 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | Vulkan | 99 | 1 | tg32 @ d16384 | 15.14 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-14B-Instruct-2512-BF16__vulkan_radv__fa1__longctx32768__single.log
+12
View File
@@ -0,0 +1,12 @@
WARNING: radv is not a conformant Vulkan implementation, testing use only.
WARNING: radv is not a conformant Vulkan implementation, testing use only.
ggml_vulkan: Found 3 Vulkan devices:
ggml_vulkan: 0 = AMD Ryzen 9 9900X3D 12-Core Processor (RADV RAPHAEL_MENDOCINO) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 65536 | int dot: 1 | matrix cores: none
ggml_vulkan: 1 = AMD Radeon AI PRO R9700 (RADV GFX1201) (radv) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
ggml_vulkan: 2 = AMD Radeon AI PRO R9700 (RADV GFX1201) (radv) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
| model | size | params | backend | ngl | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | Vulkan | 99 | 1 | pp2048 @ d32768 | 351.12 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | Vulkan | 99 | 1 | tg32 @ d32768 | 13.32 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7-nightly-rocwmma__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 1210.41 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 26.73 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7-nightly-rocwmma__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 708.36 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 22.94 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7-nightly-rocwmma__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 461.89 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 26.74 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7-nightly-rocwmma__hblt0__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 363.06 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 22.91 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7-nightly__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 958.03 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 27.59 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7-nightly__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 552.93 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 24.80 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7-nightly__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 413.39 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 27.58 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7-nightly__hblt0__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 313.00 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 24.79 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7.9-rocwmma__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 832.67 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 27.47 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7.9-rocwmma__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 459.52 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 24.45 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7.9-rocwmma__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 384.05 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 27.46 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7.9-rocwmma__hblt0__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 282.23 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 24.46 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7.9__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 963.98 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 27.76 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7.9__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 552.83 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 24.91 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7.9__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 406.44 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 27.71 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm-7.9__hblt0__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 308.45 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 24.90 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm6_4_4-rocwmma__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 868.42 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 27.51 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm6_4_4-rocwmma__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 494.21 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 24.48 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm6_4_4-rocwmma__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 397.69 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 27.47 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 295.42 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 24.47 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm6_4_4__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 1058.69 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 27.78 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm6_4_4__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 621.76 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 24.94 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm6_4_4__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 433.90 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 27.78 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm6_4_4__hblt0__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 336.61 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 24.93 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm7.1.1-rocwmma__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 832.53 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 27.47 ± 0.00 |
build: 22577583a (7312)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm7.1.1-rocwmma__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 463.80 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 24.48 ± 0.00 |
build: 22577583a (7312)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm7.1.1-rocwmma__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 383.90 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 27.46 ± 0.00 |
build: 22577583a (7312)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 281.71 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 24.45 ± 0.00 |
build: 22577583a (7312)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm7.1.1__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 964.51 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 27.76 ± 0.00 |
build: 22577583a (7312)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm7.1.1__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 544.22 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 24.91 ± 0.00 |
build: 22577583a (7312)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm7.1.1__hblt0__fa1__longctx16384__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 406.04 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 27.77 ± 0.00 |
build: 22577583a (7312)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__rocm7.1.1__hblt0__fa1__longctx32768__single.log
+10
View File
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 308.59 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 24.92 ± 0.00 |
build: 22577583a (7312)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__vulkan_amdvlk__fa1__longctx16384__single.log
+12
View File
@@ -0,0 +1,12 @@
WARNING: radv is not a conformant Vulkan implementation, testing use only.
WARNING: radv is not a conformant Vulkan implementation, testing use only.
ggml_vulkan: Found 3 Vulkan devices:
ggml_vulkan: 0 = AMD Radeon AI PRO R9700 (AMD open-source driver) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
ggml_vulkan: 1 = AMD Radeon AI PRO R9700 (AMD open-source driver) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
ggml_vulkan: 2 = AMD Ryzen 9 9900X3D 12-Core Processor (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none
| model | size | params | backend | ngl | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | Vulkan | 99 | 1 | pp2048 @ d16384 | 403.34 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | Vulkan | 99 | 1 | tg32 @ d16384 | 18.97 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__vulkan_amdvlk__fa1__longctx32768__single.log
+12
View File
@@ -0,0 +1,12 @@
WARNING: radv is not a conformant Vulkan implementation, testing use only.
WARNING: radv is not a conformant Vulkan implementation, testing use only.
ggml_vulkan: Found 3 Vulkan devices:
ggml_vulkan: 0 = AMD Radeon AI PRO R9700 (AMD open-source driver) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
ggml_vulkan: 1 = AMD Radeon AI PRO R9700 (AMD open-source driver) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
ggml_vulkan: 2 = AMD Ryzen 9 9900X3D 12-Core Processor (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none
| model | size | params | backend | ngl | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | Vulkan | 99 | 1 | pp2048 @ d32768 | 242.85 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | Vulkan | 99 | 1 | tg32 @ d32768 | 14.10 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__vulkan_radv__fa1__longctx16384__single.log
+12
View File
@@ -0,0 +1,12 @@
WARNING: radv is not a conformant Vulkan implementation, testing use only.
WARNING: radv is not a conformant Vulkan implementation, testing use only.
ggml_vulkan: Found 3 Vulkan devices:
ggml_vulkan: 0 = AMD Ryzen 9 9900X3D 12-Core Processor (RADV RAPHAEL_MENDOCINO) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 65536 | int dot: 1 | matrix cores: none
ggml_vulkan: 1 = AMD Radeon AI PRO R9700 (RADV GFX1201) (radv) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
ggml_vulkan: 2 = AMD Radeon AI PRO R9700 (RADV GFX1201) (radv) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
| model | size | params | backend | ngl | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | Vulkan | 99 | 1 | pp2048 @ d16384 | 718.51 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | Vulkan | 99 | 1 | tg32 @ d16384 | 22.17 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Ministral-3-8B-Instruct-2512-BF16__vulkan_radv__fa1__longctx32768__single.log
+12
View File
@@ -0,0 +1,12 @@
WARNING: radv is not a conformant Vulkan implementation, testing use only.
WARNING: radv is not a conformant Vulkan implementation, testing use only.
ggml_vulkan: Found 3 Vulkan devices:
ggml_vulkan: 0 = AMD Ryzen 9 9900X3D 12-Core Processor (RADV RAPHAEL_MENDOCINO) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 65536 | int dot: 1 | matrix cores: none
ggml_vulkan: 1 = AMD Radeon AI PRO R9700 (RADV GFX1201) (radv) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
ggml_vulkan: 2 = AMD Radeon AI PRO R9700 (RADV GFX1201) (radv) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
| model | size | params | backend | ngl | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | Vulkan | 99 | 1 | pp2048 @ d32768 | 442.10 ± 0.00 |
| mistral3 8B BF16 | 15.81 GiB | 8.49 B | Vulkan | 99 | 1 | tg32 @ d32768 | 18.81 ± 0.00 |
build: 6016d0bd4 (7285)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7-nightly-rocwmma__fa1__longctx16384__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7-nightly-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__fa1 __longctx16384 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7-nightly-rocwmma__fa1__longctx32768__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7-nightly-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__fa1 __longctx32768 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7-nightly-rocwmma__hblt0__fa1__longctx16384__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7-nightly-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__hblt0__fa1 __longctx16384 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7-nightly-rocwmma__hblt0__fa1__longctx32768__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7-nightly-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__hblt0__fa1 __longctx32768 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7-nightly__fa1__longctx16384__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7-nightly] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__fa1 __longctx16384 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7-nightly__fa1__longctx32768__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7-nightly] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__fa1 __longctx32768 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7-nightly__hblt0__fa1__longctx16384__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7-nightly] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__hblt0__fa1 __longctx16384 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7-nightly__hblt0__fa1__longctx32768__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7-nightly] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__hblt0__fa1 __longctx32768 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7.9-rocwmma__fa1__longctx16384__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7.9-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__fa1 __longctx16384 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7.9-rocwmma__fa1__longctx32768__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7.9-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__fa1 __longctx32768 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7.9-rocwmma__hblt0__fa1__longctx16384__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7.9-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__hblt0__fa1 __longctx16384 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7.9-rocwmma__hblt0__fa1__longctx32768__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7.9-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__hblt0__fa1 __longctx32768 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7.9__fa1__longctx16384__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7.9] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__fa1 __longctx16384 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7.9__fa1__longctx32768__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7.9] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__fa1 __longctx32768 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7.9__hblt0__fa1__longctx16384__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7.9] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__hblt0__fa1 __longctx16384 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7.9__hblt0__fa1__longctx32768__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm-7.9] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__hblt0__fa1 __longctx32768 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx16384__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm6_4_4-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__fa1 __longctx16384 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm6_4_4-rocwmma__fa1__longctx32768__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm6_4_4-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__fa1 __longctx32768 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx16384__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm6_4_4-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__hblt0__fa1 __longctx16384 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm6_4_4-rocwmma__hblt0__fa1__longctx32768__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm6_4_4-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__hblt0__fa1 __longctx32768 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm6_4_4__fa1__longctx16384__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm6_4_4] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__fa1 __longctx16384 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm6_4_4__fa1__longctx32768__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm6_4_4] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__fa1 __longctx32768 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm6_4_4__hblt0__fa1__longctx16384__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm6_4_4] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__hblt0__fa1 __longctx16384 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm6_4_4__hblt0__fa1__longctx32768__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm6_4_4] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__hblt0__fa1 __longctx32768 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx16384__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm7.1.1-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__fa1 __longctx16384 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm7.1.1-rocwmma__fa1__longctx32768__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm7.1.1-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__fa1 __longctx32768 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx16384__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm7.1.1-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__hblt0__fa1 __longctx16384 failed (exit 0)
benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm7.1.1-rocwmma__hblt0__fa1__longctx32768__dual.log
+9
View File
@@ -0,0 +1,9 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
✖ ! [rocm7.1.1-rocwmma] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__hblt0__fa1 __longctx32768 failed (exit 0)

Some files were not shown because too many files have changed in this diff Show More