Jinyang Yuan 5339d367ce [perf] Reduce the workspace size of FP4 activation scales for MoE (#4303) ... Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>		2025-05-30 09:03:52 +08:00
..
allReduce	Cherry pick feat/llama4 to main (#4739)	2025-05-30 05:28:40 +08:00
cudaCoreGemm	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
fused_gated_gemm	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
sampling	test: Test OOB access issue in penaltyKernel for endId=-1 (#4035)	2025-05-05 10:24:28 -07:00
smoothQuant	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
weightOnly	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
banRepeatNGramsKernelsTest.cpp	chore: remove usernames from comments (#3291)	2025-04-05 13:44:28 +08:00
CMakeLists.txt	feat: support kv cache reuse for MLA (#3571)	2025-05-15 15:22:21 +08:00
decodingKernelTest.cpp	chore: remove usernames from comments (#3291)	2025-04-05 13:44:28 +08:00
logitsBitmaskTest.cpp	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
mixtureOfExpertsTest.cu	[perf] Reduce the workspace size of FP4 activation scales for MoE (#4303)	2025-05-30 09:03:52 +08:00
mlaPreprocessTest.cu	[TRTLLM-5070][feat] Support FP8 KV Cache Reuse for MLA (#4535)	2025-05-23 19:47:50 +08:00
ropeTest.cu	feat: Add FP8 support for SM 120 (#3248)	2025-04-14 16:05:41 -07:00
shiftKCacheKernelTest.cu	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
stopCriteriaKernelsTest.cpp	chore: remove usernames from comments (#3291)	2025-04-05 13:44:28 +08:00