cjw/amd-r9700-ai-toolboxes
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

benchmakr updates

Browse Source
This commit is contained in:
Donato Capitella
2025-12-17 08:01:12 +00:00
parent 29da348bb8
commit 2e8bef127f
818 changed files with 30850 additions and 24154 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/results/llama-2-7b.Q4_0__rocm-7.9__fa1__longctx32768__single.log
+3 -3
View File
@@ -4,7 +4,7 @@ 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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 565.30 ± 0.00 |
| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 24.00 ± 0.00 |
| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 567.29 ± 0.00 |
| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 26.87 ± 0.00 |
build: 6016d0bd4 (7285)
build: 2aa45ef9e (7423)