TensorRT-LLMs

mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-22 11:42:41 +08:00

History

Jin Li 3454eacd74 [https://nvbugs/5546510 ][fix] Move torch.cuda.Stream out of torch com… (#8494 ) Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com> Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com> Signed-off-by: Mike Iovine <miovine@nvidia.com>		2025-11-20 12:43:13 -05:00
..
__init__.py	Update TensorRT-LLM (#2755 )	2025-02-11 03:01:00 +00:00
_util.py	[TRTLLM-7723][feat] sampling using FlashInfer.sampling (#8581 )	2025-11-11 03:21:19 -08:00
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	[TRTLLM-8831][feat] Enable early exit with overlap scheduler (#8587 )	2025-11-17 18:07:13 +01:00
executor_request_queue.py	[None][chore] Remove is_disaggregated param in executor request queue (#9049 )	2025-11-12 13:37:15 -05:00
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-8831][feat] Enable early exit with overlap scheduler (#8587 )	2025-11-17 18:07:13 +01:00
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	[TRTLLM-8477][chore] Replace KvCacheConfigCpp with KvCacheConfig inside PyExecutor (#8259 )	2025-10-13 14:55:36 +08:00
model_engine.py	[https://nvbugs/5546510 ][fix] Move torch.cuda.Stream out of torch com… (#8494 )	2025-11-20 12:43:13 -05:00
model_loader.py	[TRTLLM-9065][chore] remove PyTorchConfig completely (#8856 )	2025-11-06 22:37:03 -08:00
py_executor_creator.py	[TRTLLM-8136][feat] Dynamic draft length in spec decode (stage 1). (#8194 )	2025-11-18 11:13:39 -05:00
py_executor.py	[TRTLLM-8136][feat] Dynamic draft length in spec decode (stage 1). (#8194 )	2025-11-18 11:13:39 -05:00
resource_manager.py	[#6507 ][fix] Fix precision issue due to KV layout mismatch for split/concat kernels (#6917 )	2025-11-13 12:14:58 +08:00
sampler.py	[https://nvbugs/5661877 ][fix] fix test regression in TestBatchedSampling::test_samples (#9215 )	2025-11-19 01:44:44 -08:00
sampling_utils_flashinfer.py	[TRTLLM-8377][test] unit tests for TorchSampler batched sampling (#9012 )	2025-11-11 07:16:42 -08:00
sampling_utils.py	[TRTLLM-7723][feat] sampling using FlashInfer.sampling (#8581 )	2025-11-11 03:21:19 -08:00
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