kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
4d040b50b7
TensorRT-LLMs/cpp/kernels
History
Bruce-Lee-LY 8c82ee2803
[fix] xqa precision for fp16/bf16 kv cache (#6573) 
Signed-off-by: Bruce-Lee-LY <yong-li14@tsinghua.org.cn>
Co-authored-by: Bruce-Lee-LY <yong-li14@tsinghua.org.cn>
2025-08-04 14:34:20 +08:00
..
fmha_v2 hopper-style context MLA (#5713) 2025-07-23 14:37:20 +08:00
xqa [fix] xqa precision for fp16/bf16 kv cache (#6573) 2025-08-04 14:34:20 +08:00