< cd ../gallery
[DevTools]
vllm_benchmark_block_fp8 by massif-01
Automated Triton w8a8 block FP8 kernel tuning tool for vLLM. Auto-detects model architecture, supports Qwen3-Coder-30B-A3B-Instruct-FP8/DeepSeek-V3/custom models, multi-GPU parallel tuning, and generates optimized kernel configs for quantization. Maintained by massif-01 on GitHub, where it has earned 13 stars from the community.
# install
pip install vllm_benchmark_block_fp8more vLLM repos
DevTools
Reproducible recipe: serve abliterated Gemma-4-12B (gemma4_unified) at 50-118 tok/s on no-NVLink Blackwell (SM120) via vLLM nightly + ModelOpt FP8/NVFP4 + MTP spec-decode. Maintained by lna-lab on GitHub, where it has earned 15 stars from the community.
4mo ago
DevTools
The official implementation of CVPR Workshop 2025 paper: Window Token Concatenation for Efficient Visual Large Language Models. Maintained by JackYFL on GitHub, where it has earned 11 stars from the community.
1y ago
DevTools
[AAAI 2025 oral] Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit. Maintained by qizhou000 on GitHub, where it has earned 19 stars from the community.
1y ago
