bhsueh_NV b87f26ee2a chore: remove useless allgather (#3751) ... * remove useless allgather Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com> * fix pre-commit issue Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com> --------- Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>		2025-04-22 21:26:22 +08:00
..
__init__.py	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
_util.py	chore: remove useless allgather (#3751)	2025-04-22 21:26:22 +08:00
config.py	feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387)	2025-04-21 10:01:33 +08:00
cuda_graph_runner.py	Support CUDA graphs for EAGLE3 (#3176)	2025-04-17 04:53:50 +08:00
decoder.py	refactor: collect executor and decoder states into dataclass (#3234)	2025-04-15 16:31:45 +08:00
guided_decoder.py	Update (#2978)	2025-03-23 16:39:35 +08:00
kv_cache_transceiver.py	bug: Fix hang bug when context server doesn't have enough capacity for KV Cache (#3095)	2025-04-21 15:16:55 +08:00
layerwise_nvtx_marker.py	Update TensorRT-LLM (#2849)	2025-03-04 18:44:00 +08:00
llm_request.py	fix: Proper error bubbling for PyExecutor (#3321)	2025-04-15 14:49:46 +08:00
model_engine.py	test: Unwaive Llama 3.1 with torch compile test (#3475)	2025-04-22 10:41:56 +08:00
py_executor_creator.py	Fix/executor bugs (#3681)	2025-04-22 07:23:27 +08:00
py_executor.py	Fix/executor bugs (#3681)	2025-04-22 07:23:27 +08:00
resource_manager.py	feat: allocate minimal blocks per window size (#3028)	2025-04-17 16:04:57 +08:00
scheduler.py	refactor: collect executor and decoder states into dataclass (#3234)	2025-04-15 16:31:45 +08:00