TensorRT-LLMs

mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00

History

Pengyun Lin 039f7e3118 [https://nvbugspro.nvidia.com/bug/5243740 ][fix] deduce default max_tokens for trtllm-serve (#4265 ) * Deduce default max_tokens for trtllm-serve Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com> * Improve executor_config.max_seq_len assignment in TRT workflow Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com> * Enhance error message Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com> * Add deduced max_tokens test Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com> --------- Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>		2025-05-19 00:34:40 +08:00
..
__init__.py	cacheTransceiver buffer manager (#3798 )	2025-04-27 11:48:15 +08:00
_perf_evaluator.py	chore: Cleanup deprecated APIs from LLM-API (part 1/2) (#3732 )	2025-05-07 13:20:25 +08:00
build_cache.py	Update TensorRT-LLM (#2413 )	2024-11-05 16:27:06 +08:00
disagg_utils.py	feat: add kv cache aware router (#3831 )	2025-05-12 07:23:57 -04:00
llm_args.py	add changes for fp8, nemotron-nas, API (#4180 )	2025-05-18 23:27:25 +08:00
llm_utils.py	fix: trtllm-bench build trt engine on slurm (#3825 )	2025-04-27 22:26:23 +08:00
llm.py	[https://nvbugspro.nvidia.com/bug/5243740 ][fix] deduce default max_tokens for trtllm-serve (#4265 )	2025-05-19 00:34:40 +08:00
mgmn_leader_node.py	fix: trtllm-bench build trt engine on slurm (#3825 )	2025-04-27 22:26:23 +08:00
mgmn_worker_node.py	Update TensorRT-LLM (#2333 )	2024-10-15 15:28:40 +08:00
mpi_session.py	chore: Mass Integration 0.19 (#4255 )	2025-05-16 10:53:25 +02:00
reasoning_parser.py	feat: add deepseek-r1 reasoning parser to trtllm-serve (#3354 )	2025-05-06 08:13:04 +08:00
tokenizer.py	test [TRTLLM-4477,TRTLLM-4481]: Accuracy test improvement (Part 3.5): Support GSM8K and GPQA (#3483 )	2025-04-22 07:38:16 +08:00
tracer.py	Update TensorRT-LLM (#2413 )	2024-11-05 16:27:06 +08:00
trtllm-llmapi-launch	fix hmac in remote mpi session (#3649 )	2025-04-18 17:47:51 +08:00
utils.py	fix: trtllm-bench build trt engine on slurm (#3825 )	2025-04-27 22:26:23 +08:00