| .. |
|
__init__.py
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
_util.py
|
[TRTLLM-6780][fix] Add multimodal data to dummy requests during memory profiling (#7539)
|
2025-10-16 17:49:22 +02:00 |
|
config_utils.py
|
[None][chore] Refine qwen3-next implementation. (#8064)
|
2025-09-30 15:05:13 -04:00 |
|
config.py
|
[None][chore] Cherry-pick from (#7598) Make low_precision_combine as a llm arg (#7898)
|
2025-09-28 22:32:33 -04:00 |
|
cuda_graph_runner.py
|
[None][feat] reuse cudagraph memory pool in normal forward flow (#8095)
|
2025-10-16 07:08:44 +08:00 |
|
executor_request_queue.py
|
[TRTLLM-7349][feat] Adding new orchestrator type -- ray (#7520)
|
2025-10-04 08:12:24 +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-8209][feat] Support new structural tag API (upgrade XGrammar to 0.1.25) (#7893)
|
2025-09-23 09:10:09 +08:00 |
|
guided_decoder.py
|
[None][fix] Disable torch.compile for CapturableGuidedDecoder (#7871)
|
2025-09-22 10:04:30 +08:00 |
|
handle_additional_outputs.py
|
[TRTLLM-4517] [feat] Additional model outputs (#7206)
|
2025-10-13 15:33:18 +02:00 |
|
handle_logits.py
|
[TRTLLM-8031][feat] Add chunked return_generation_logits logic (#7831)
|
2025-10-01 12:47:07 -04:00 |
|
kv_cache_connector.py
|
[None][feat] Enable CUDA graph support for KvConnectorWorker API (#8275)
|
2025-10-17 18:09:03 -04:00 |
|
kv_cache_transceiver.py
|
[TRTLLM-7964][infra] Set nixl to default cache transceiver backend (#7926)
|
2025-10-19 19:24:43 +08:00 |
|
layerwise_nvtx_marker.py
|
Update TensorRT-LLM (#2849)
|
2025-03-04 18:44:00 +08:00 |
|
llm_request.py
|
[None][feat] Support cached tokens for Openai server (#7637)
|
2025-10-16 20:51:37 +08:00 |
|
make_decoding_batch_input_output.py
|
feat: Optimize TRTLLM Sampler perf single beam single step (#5550)
|
2025-07-07 15:44:47 +02:00 |
|
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
|
[None][feat] Enable CUDA graph support for KvConnectorWorker API (#8275)
|
2025-10-17 18:09:03 -04:00 |
|
model_loader.py
|
[TRTLLM-8536][feat] Add the sparse attention framework and one use case--RocketKV support (#8086)
|
2025-10-14 08:23:16 -07:00 |
|
py_executor_creator.py
|
[TRTLLM-8480][chore] clean create_py_executor API (#8412)
|
2025-10-17 23:52:02 -04:00 |
|
py_executor.py
|
[TRTLLM-8436][feat] batched sampling and top-k logprobs improvements (#8398)
|
2025-10-20 11:15:41 +02:00 |
|
resource_manager.py
|
[None][fix] Fix KV event consumption (#6346)
|
2025-10-18 15:41:26 -07:00 |
|
sampler.py
|
[None][fix] restore list[list[list[int]]] in add_token (#8502)
|
2025-10-20 22:34:57 -04:00 |
|
sampling_utils.py
|
[TRTLLM-8436][feat] batched sampling and top-k logprobs improvements (#8398)
|
2025-10-20 11:15:41 +02:00 |
|
scheduler.py
|
[https://nvbugs/5528405][fix] Set up draft_tokens before scheduling (#7903)
|
2025-09-24 09:56:17 +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 |
