Fanrong Li 156f6453dc [TRTLLM-9798][feat] Change to use new DeepGEMM MQA sm100 kernel for MTP-3 (#10226) ... Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>		2025-12-24 14:39:12 +08:00
..
sparse	[TRTLLM-9798][feat] Change to use new DeepGEMM MQA sm100 kernel for MTP-3 (#10226)	2025-12-24 14:39:12 +08:00
test_attention_mla.py	[TRTLLM-8803][feat] Add rope and uk-bgemm overlap for mla generation (#8495)	2025-11-06 17:39:57 +08:00
test_attention_no_cache.py	[None][ci] move unittests to sub-directories (#6635)	2025-08-20 05:42:22 -04:00
test_attention.py	[#6507][fix] Fix precision issue due to KV layout mismatch for split/concat kernels (#6917)	2025-11-13 12:14:58 +08:00
test_flashinfer_attention.py	[#6507][fix] Fix precision issue due to KV layout mismatch for split/concat kernels (#6917)	2025-11-13 12:14:58 +08:00
test_flashinfer_star_attn.py	[#6507][fix] Fix precision issue due to KV layout mismatch for split/concat kernels (#6917)	2025-11-13 12:14:58 +08:00
test_trtllm_flashinfer_symbol_collision.py	[#9717][chore] Refactor MoE code to use enums (#9910)	2025-12-22 15:14:56 -05:00
test_vanilla_attention.py	[None][ci] move unittests to sub-directories (#6635)	2025-08-20 05:42:22 -04:00