vllm/csrc/quantization/fp8 at b8afa8b95a4eee008a9b72440620113e5bfbe962 - vllm - Gitea: Git with a cup of macha paffe

karylab_agents/vllm

forked from Karylab-cklius/vllm

Files

T

History

12628d3c78 [Kernel] Optimize FP8 support for MoE kernel / Mixtral via static scales (#4343 )

Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

2024-04-27 04:49:59 +00:00

..

Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) (#3290 )

2024-04-03 14:15:55 -07:00

fp8_cuda_kernels.cu

[Kernel] Optimize FP8 support for MoE kernel / Mixtral via static scales (#4343 )

2024-04-27 04:49:59 +00:00