A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 3, 05:30 UTC
[Bugfix] Use enable_sm120_family for per-tensor FP8 CUTLASS kernels on SM12.1 (#41215)
Signed-off-by: j9smith <j.smith9103@outlook.com> Signed-off-by: Joel Smith <j.smith9103@outlook.com> Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
Joel Smith committed
May 20, 2026 at 15:10 UTC
644b2a28e7eb3b11191f157416cfedebd2da995b
No changes.