TensorRT-LLMs

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

History

Thor Johnsen 95049eea86 [https://nvbugs/5627710 ][fix] Fix synchronization bugs in KvCacheTransferManager that can cause corrupted blocks (#9056 ) Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com> Signed-off-by: Thor Johnsen <41591019+thorjohnsen@users.noreply.github.com> Co-authored-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com> Co-authored-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>		2025-12-02 09:10:21 -06:00
..
__init__.py	Update TensorRT-LLM (#2755 )	2025-02-11 03:01:00 +00:00
_util.py	[TRTLLM-6756][feat] Add Beam Search to TorchSampler (#8509 )	2025-12-01 18:48:04 +01:00
config_utils.py	[None][fix] fix config loading for DeepSeek-V3.2 in trtllm-bench (#8729 )	2025-10-29 05:17:16 -07:00
cuda_graph_runner.py	[https://nvbugs/5698581 ][fix] Init draft tokens for CUDA graph dummy request (#9505 )	2025-11-27 13:05:37 +08:00
executor_request_queue.py	[TRTLLM-5971][feat] Integrate helix parallelism (#9342 )	2025-11-29 15:17:30 -08:00
finish_reason.py	[TRTLLM-5974][feat] Support disaggregated serving in TRTLLM Sampler (#5328 )	2025-06-25 17:41:36 +02:00
grammar_matcher.py	[TRTLLM-8763][chore] Deprecate pybind based GuidedDecodingConfig usage in torch backend (#8717 )	2025-10-29 20:37:14 +08:00
guided_decoder.py	[TRTLLM-8763][chore] Deprecate pybind based GuidedDecodingConfig usage in torch backend (#8717 )	2025-10-29 20:37:14 +08:00
handle_additional_outputs.py	[TRTLLM-8831][feat] Enable early exit with overlap scheduler (#8587 )	2025-11-17 18:07:13 +01:00
handle_logits.py	[TRTLLM-8831][feat] Enable early exit with overlap scheduler (#8587 )	2025-11-17 18:07:13 +01:00
kv_cache_connector.py	[None][feat] Support KV Connector with Disagg Prefill Worker (#8246 )	2025-10-24 11:09:06 -07:00
kv_cache_transceiver.py	[None][feat] Have ability to cancel disagg request if KV cache resource are exhausted (#9155 )	2025-11-18 20:59:17 -05:00
layerwise_nvtx_marker.py	Update TensorRT-LLM (#2849 )	2025-03-04 18:44:00 +08:00
llm_request.py	[TRTLLM-5971][feat] Integrate helix parallelism (#9342 )	2025-11-29 15:17:30 -08:00
make_decoding_batch_input_output.py	[None][refactor] decoding inputs, part 2 (#5799 )	2025-11-18 14:38:51 +01:00
mamba_cache_manager.py	[https://nvbugs/5537996 ][fix] Let KV cache manager block initialization be aware whether it is doing a dry run or not (#9093 )	2025-11-25 17:27:11 +08:00
model_engine.py	[https://nvbugs/5667774 ][fix] Refine Piecewise Cuda Graph Condition for DP (#9393 )	2025-12-02 21:09:15 +08:00
model_loader.py	[TRTLLM-9293][feat] Enable partial weight loading to support streaming update weights (#9224 )	2025-11-26 10:59:06 +08:00
py_executor_creator.py	[None][chore] Weekly mass integration of release/1.1 -- rebase (#9522 )	2025-11-29 21:48:48 +08:00
py_executor.py	[TRTLLM-909][feat] Overlap context chunks in pipeline parallel mode (#9308 )	2025-11-25 22:11:51 +01:00
resource_manager.py	[https://nvbugs/5627710 ][fix] Fix synchronization bugs in KvCacheTransferManager that can cause corrupted blocks (#9056 )	2025-12-02 09:10:21 -06:00
sampler.py	[TRTLLM-6756][feat] Add Beam Search to TorchSampler (#8509 )	2025-12-01 18:48:04 +01:00
sampling_utils_flashinfer.py	[TRTC-1943][feat] Env vars override support in LLM API (#9104 )	2025-12-01 10:04:49 -08:00
sampling_utils.py	[TRTLLM-6756][feat] Add Beam Search to TorchSampler (#8509 )	2025-12-01 18:48:04 +01:00
scheduler.py	[TRTLLM-8483][chore] Refine scheduler_config and peft_cache_config in create_py_executor (#8451 )	2025-10-22 08:33:48 +08:00
seq_slot_manager.py	[https://nvbugs/5394392 ][fix] Enlarge scheduler capacity under disagg bs == 1 (#6537 )	2025-08-15 09:52:06 -07:00