qwen-speedlab / scripts

173 kB

Ctrl+K

1 contributor

History: 2 commits

simonlesaumon

Add custom CUDA kernels + demo scripts

727757f verified 7 days ago

bench_openai_api.py

20.4 kB
Upload folder using huggingface_hub 8 days ago
bench_vllm.py

12.8 kB
Upload folder using huggingface_hub 8 days ago
benchmark.sh

4.66 kB
Add custom CUDA kernels + demo scripts 7 days ago
benchmark_now.sh

5.43 kB
Upload folder using huggingface_hub 8 days ago
collect_gpu_stats.sh

2.27 kB
Upload folder using huggingface_hub 8 days ago
common.sh

3.21 kB
Add custom CUDA kernels + demo scripts 7 days ago
download_best_model.py

9.34 kB
Upload folder using huggingface_hub 8 days ago
fix_gpu_host.sh

2.86 kB
Upload folder using huggingface_hub 8 days ago
inspect_model.py

13.3 kB
Upload folder using huggingface_hub 8 days ago
run_all.sh

5.53 kB
Upload folder using huggingface_hub 8 days ago
serve-baseline.sh

1.39 kB
Add custom CUDA kernels + demo scripts 7 days ago
serve-dflash.sh

2.12 kB
Add custom CUDA kernels + demo scripts 7 days ago
serve-mtp.sh

1.95 kB
Add custom CUDA kernels + demo scripts 7 days ago
serve-turbo.sh

1.75 kB
Add custom CUDA kernels + demo scripts 7 days ago
serve-turboq-max.sh

2.14 kB
Add custom CUDA kernels + demo scripts 7 days ago
serve_sglang.sh

2.02 kB
Upload folder using huggingface_hub 8 days ago
serve_vllm.sh

8.82 kB
Upload folder using huggingface_hub 8 days ago
serve_vllm_optimized.sh

7.67 kB
Upload folder using huggingface_hub 8 days ago
setup_runpod.sh

5.34 kB
Upload folder using huggingface_hub 8 days ago
sweep_advanced.py

29.3 kB
Upload folder using huggingface_hub 8 days ago
sweep_vllm_configs.py

30.3 kB
Upload folder using huggingface_hub 8 days ago