HuiGao-NV 3ed3bbcb5d Fix: pass allreduce strategy to pytorchConfig (#5746) ... Signed-off-by: Hui Gao <huig@nvidia.com>		2025-07-04 21:32:13 +09:00
..
__init__.py	[TRTLLM-5530][BREAKING CHANGE]: enhance the llm args pytorch config part 1(cuda_graph_config) (#5014)	2025-06-30 11:05:40 +08:00
build_cache.py	Update TensorRT-LLM (#2413)	2024-11-05 16:27:06 +08:00
disagg_utils.py	feat: Dynamically remove servers in PD (#5270)	2025-06-25 09:50:04 +08:00
llm_args.py	Fix: pass allreduce strategy to pytorchConfig (#5746)	2025-07-04 21:32:13 +09:00
llm_utils.py	[TRTLLM-5530][BREAKING CHANGE]: enhance the llm args pytorch config part 1(cuda_graph_config) (#5014)	2025-06-30 11:05:40 +08:00
llm.py	Raise shut down error for each request (#4936)	2025-07-04 18:58:24 +09:00
mgmn_leader_node.py	fix[nvbug5298640]: trtllm-llmapi-launch multiple LLM instances (#4727)	2025-06-19 06:13:53 +08:00
mgmn_worker_node.py	Update TensorRT-LLM (#2333)	2024-10-15 15:28:40 +08:00
mpi_session.py	fix[nvbug5298640]: trtllm-llmapi-launch multiple LLM instances (#4727)	2025-06-19 06:13:53 +08:00
reasoning_parser.py	feat: add deepseek-r1 reasoning parser to trtllm-serve (#3354)	2025-05-06 08:13:04 +08:00
tokenizer.py	perf: Use tokenizers API to optimize incremental detokenization perf (#5574)	2025-07-01 09:35:25 -04:00
tracer.py	Update TensorRT-LLM (#2413)	2024-11-05 16:27:06 +08:00
trtllm-llmapi-launch	fix[nvbug5298640]: trtllm-llmapi-launch multiple LLM instances (#4727)	2025-06-19 06:13:53 +08:00
utils.py	chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)	2025-05-28 18:43:04 +08:00