| .. |
|
__init__.py
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
_util.py
|
[https://nvbugs/5322131][feat] Multi-LoRA serving with CUDA Graph (#8279)
|
2026-01-22 14:01:18 +01:00 |
|
config_utils.py
|
[None][feat] Eagle: MLA Based Eagle (#9677)
|
2026-01-02 13:45:07 -05:00 |
|
cuda_graph_runner.py
|
[None][refactor] Unify the usage of MPIDist and TorchDist. (#10380)
|
2026-01-14 14:05:47 +08:00 |
|
executor_request_queue.py
|
[TRTLLM-10059][feat] Use global unique id as disagg request id (#10187)
|
2026-01-21 22:52:34 -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
|
[https://nvbugs/5669671][fix] Support GuidedDecoder with sharded logits (#10698)
|
2026-01-16 11:04:26 +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 |
|
hang_detector.py
|
[None][feat] Hang detection for executor loop and worker. (#10480)
|
2026-01-13 02:34:32 -05:00 |
|
kv_cache_connector.py
|
[None][feat] KV Connector Support for MTP (#10932)
|
2026-01-23 18:58:26 -05:00 |
|
kv_cache_transceiver.py
|
[TRTLLM-9942][feat] new request states and kvcache transceiver APIs in generation-first disagg (#10406)
|
2026-01-15 19:18:21 +08:00 |
|
layerwise_nvtx_marker.py
|
Update TensorRT-LLM (#2849)
|
2025-03-04 18:44:00 +08:00 |
|
llm_request.py
|
[https://nvbugs/5322131][feat] Multi-LoRA serving with CUDA Graph (#8279)
|
2026-01-22 14:01:18 +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-10062][feat] Enable MTP for Nemotron Super (#10754)
|
2026-01-26 11:23:26 -05:00 |
|
model_engine.py
|
[https://nvbugs/5322131][feat] Multi-LoRA serving with CUDA Graph (#8279)
|
2026-01-22 14:01:18 +01:00 |
|
model_loader.py
|
[#8241][feat] Support model_kwargs for pytorch backend (#10351)
|
2026-01-21 20:51:38 -08:00 |
|
py_executor_creator.py
|
[None][feat] KV Connector Support for MTP (#10932)
|
2026-01-23 18:58:26 -05:00 |
|
py_executor.py
|
[TRTLLM-10560][fix] Fix the time of pause() for overlap scheduler (#10943)
|
2026-01-27 13:18:34 +08:00 |
|
resource_manager.py
|
[TRTLLM-10062][feat] Enable MTP for Nemotron Super (#10754)
|
2026-01-26 11:23:26 -05:00 |
|
sampler.py
|
[TRTLLM-9735][feat] Add processed logprobs functionality to TorchSampler (#9675)
|
2026-01-16 10:52:41 -08:00 |
|
sampling_utils_flashinfer.py
|
[https://nvbugs/5791242][fix] workaround for flashinfer.sampling.sampling_from_logits (#10713)
|
2026-01-25 18:12:21 +08:00 |
|
sampling_utils.py
|
[TRTLLM-9735][feat] Add processed logprobs functionality to TorchSampler (#9675)
|
2026-01-16 10:52:41 -08:00 |
|
scheduler.py
|
[TRTLLM-10029][scheduler] Re-implement MicroBatchScheduler and CapacityScheduler in Python (#10273)
|
2026-01-20 10:31:13 +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 |
