cjw/amd-r9700-ai-toolboxes
1
0
Fork 0
Code Issues Pull Requests Actions 7 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/llama-2-7b.Q4_0__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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | pp2048 @ d16384 | 989.11 ± 0.00 |
| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | tg32 @ d16384 | 38.36 ± 0.00 |
build: 22577583a (7312)