clef-flash-FP8-Dynamic / vllm_plugin

Commit History

vllm_plugin: host-side lm_head under TP, int32 id fix, --flashinfer-autotune (auto off for TP>1)
7b43c2d
verified

kurcontko commited on

Upload clef-flash-FP8-Dynamic (vLLM plugin + SystemOne server)
a58490a
verified

kurcontko commited on