Files
amd-strix-halo-toolboxes/benchmark/results/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL-00001-of-00002__rocm6_4_2__fa1.log
T
Donato Capitella a9618d881b - Corrected typo in WMMA (was spelt wrong as waam)
- Included rocm-7rc-rocwmma toolbox
- Included updated results from benchmarks including rocm 7rc with ROMWMMA and hipBLASLt
2025-08-10 13:21:06 +01:00

11 lines
770 B
Plaintext

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: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 999 | 1 | 0 | pp512 | 122.98 ± 0.59 |
| llama4 17Bx16E (Scout) Q4_K - Medium | 57.73 GiB | 107.77 B | ROCm | 999 | 1 | 0 | tg128 | 17.53 ± 0.00 |
build: 79c1160b (6123)