Jhao-Ting Chen 54f68287fc fix precompiled multi_query_token kernel not having is_fp8_out hash key (#6279) ... Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>		2025-07-25 20:45:53 -04:00
..
batch_manager	[nvbug/5374773] chore: Add a runtime flag to enable fail fast when attn window is too large to fit at least one sequence in KV cache (#5974)	2025-07-25 18:10:40 -04:00
common	[https://nvbugs/5387771] fix deadlocks due to insufficient numSemaphores (#6262)	2025-07-23 11:20:55 +08:00
cutlass_extensions/include/cutlass_extensions	Fix GEMM+AR fusion on blackwell (#5563)	2025-07-09 08:48:47 +08:00
deep_ep	fix: Ensure mlx5 library is installed for deep_ep and remove deprecated python bindings (#6189)	2025-07-20 10:38:51 +08:00
executor	[nvbug/5374773] chore: Add a runtime flag to enable fail fast when attn window is too large to fit at least one sequence in KV cache (#5974)	2025-07-25 18:10:40 -04:00
executor_worker	Update TensorRT-LLM (#2792)	2025-02-18 21:27:39 +08:00
kernels	fix precompiled multi_query_token kernel not having is_fp8_out hash key (#6279)	2025-07-25 20:45:53 -04:00
layers	refactor: Remove enforced sorted order of batch slots (#3502)	2025-07-14 17:23:02 +02:00
nanobind	fix: integration tests with nanobind (#6326)	2025-07-25 09:23:20 +08:00
plugins	fix TMA error with GEMM+AR on TP=2 (#6075)	2025-07-18 10:26:08 +08:00
pybind	[nvbug/5374773] chore: Add a runtime flag to enable fail fast when attn window is too large to fit at least one sequence in KV cache (#5974)	2025-07-25 18:10:40 -04:00
runtime	fix TMA error with GEMM+AR on TP=2 (#6075)	2025-07-18 10:26:08 +08:00
testing	fix: Improve chunking test and skip empty kernel calls (#5710)	2025-07-04 09:08:15 +02:00
thop	[https://nvbugs/5340941] - fix: Correct custom ops used by Qwen3 Moe … (#6285)	2025-07-25 14:49:45 +08:00
CMakeLists.txt	feat: binding type build argument (pybind, nanobind) (#5802)	2025-07-11 00:48:50 +09:00