zhhuang-nv 8452775db8 [TRTLLM-5070][feat] Support FP8 KV Cache Reuse for MLA (#4535) ... * optimize kv cache reuse workflow for MLA write kv cache first and only call up-projection GEMM once relax contiguous requirements of k/v for setting paged kv cache return two contiguous tensors when loading MLA KV Cache Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * support fp8 kv cache for MLA kv cache reuse Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * resolve comments Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> --------- Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>		2025-05-23 19:47:50 +08:00
..
__init__.py	feat: Add group_rms_norm kernel to normalize multiple inputs in a single operator. (#3438)	2025-05-02 13:25:30 +08:00
flashinfer.py	[https://nvbugs/5123103][fix] Fix torch compile for DeepSeekV3 (#3952)	2025-05-19 22:12:25 +08:00
interface.py	[https://nvbugs/5123103][fix] Fix torch compile for DeepSeekV3 (#3952)	2025-05-19 22:12:25 +08:00
star_flashinfer.py	Remove dummy forward path (#3669)	2025-04-18 16:17:50 +08:00
trtllm.py	[TRTLLM-5070][feat] Support FP8 KV Cache Reuse for MLA (#4535)	2025-05-23 19:47:50 +08:00
utils.py	[feat] Integrate Hopper chunked attention kernels (#4330)	2025-05-22 17:10:57 -04:00
vanilla.py	Remove dummy forward path (#3669)	2025-04-18 16:17:50 +08:00