updated benchmarks

This commit is contained in:
Donato Capitella
2025-11-30 13:47:32 +00:00
parent 301424c1f7
commit 3d9087c39b
184 changed files with 3159 additions and 3222 deletions
@@ -6,7 +6,7 @@ ggml_vulkan: 1 = AMD Radeon AI PRO R9700 (RADV GFX1201) (radv) | uma: 0 | fp16:
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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | Vulkan | 99 | 1 | pp512 | 2385.27 ± 97.69 |
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | Vulkan | 99 | 1 | tg128 | 23.12 ± 0.96 |
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | Vulkan | 99 | 1 | pp512 | 2200.62 ± 29.19 |
| gpt-oss 20B BF16 | 38.97 GiB | 20.91 B | Vulkan | 99 | 1 | tg128 | 25.87 ± 1.07 |
build: fa0465954 (7205)