Hugging Face's logo

kurcontko
/
clef-flash-FP8-Dynamic

Safetensors
vllm
qwen3_5
clef
systemone
jev
fp8
compressed-tensors
llm-compressor
qwen3.5
structured-output
classification
Model card Files
xet
 Community
clef-flash-FP8-Dynamic / vllm_plugin /clef_vllm /server.py

Commit History

  1. vllm_plugin: host-side lm_head under TP, int32 id fix, --flashinfer-autotune (auto off for TP>1)

    kurcontko
    Verified signature
    7b43c2d

  1. Upload clef-flash-FP8-Dynamic (vLLM plugin + SystemOne server)

    kurcontko
    Verified signature
    a58490a