Fanrong Li 8f144d9282 [TRTLLM-9416][feat] Skip DS-v3.2 indexer MQA and Top-K for short sequences. (#9524) ... Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>		2025-12-15 12:42:25 +08:00
..
sparse	[TRTLLM-9416][feat] Skip DS-v3.2 indexer MQA and Top-K for short sequences. (#9524)	2025-12-15 12:42:25 +08:00
__init__.py	[TRTLLM-8536][feat] Add the sparse attention framework and one use case--RocketKV support (#8086)	2025-10-14 08:23:16 -07:00
flashinfer.py	[#6507][fix] Fix precision issue due to KV layout mismatch for split/concat kernels (#6917)	2025-11-13 12:14:58 +08:00
interface.py	[TRTLLM-8160][feat] Add draft token tree runtime on CDL (#8586)	2025-11-25 09:40:55 -05:00
star_flashinfer.py	[#6507][fix] Fix precision issue due to KV layout mismatch for split/concat kernels (#6917)	2025-11-13 12:14:58 +08:00
trtllm.py	[TRTLLM-9468][chore] Update disagg benchmarking scripts to support context parallelism (#9720)	2025-12-12 22:29:41 -08:00
utils.py	[TRTLLM-8535][feat] Support DeepSeek V3.2 with FP8 + BF16 KV cache/NVFP4 + BF16 KV cache (#8405)	2025-10-24 13:40:41 -04:00
vanilla.py	[TRTLLM-8536][feat] Add the sparse attention framework and one use case--RocketKV support (#8086)	2025-10-14 08:23:16 -07:00