| .. |
|
__init__.py
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
_util.py
|
[None][fix] Refactoring to avoid circular import when importing torch models (#6720)
|
2025-08-11 18:00:42 -04:00 |
|
config_utils.py
|
feat: support kv cache reuse for MLA (#3571)
|
2025-05-15 15:22:21 +08:00 |
|
config.py
|
[None][feat] CUTLASS MoE FC2+Finalize fusion (#3294)
|
2025-08-12 15:56:48 +08:00 |
|
cuda_graph_runner.py
|
[TRTLLM-6650][fix] Enhance CUDA graph + Beam search to correctly handle padding (#6665)
|
2025-08-08 14:00:33 +02:00 |
|
executor_request_queue.py
|
[None][fix] Remove lock related typo in py_executor (#6653)
|
2025-08-08 17:48:57 +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-6409][feat] Enable guided decoding with speculative decoding (part 1: two-model engine) (#6300)
|
2025-08-07 05:53:48 -04:00 |
|
guided_decoder.py
|
[TRTLLM-2285][feat] Enable guided decoding with CUDA graph padding and draft model chunked prefill (#6774)
|
2025-08-12 09:30:06 +08:00 |
|
handle_logits.py
|
feat: Optimize TRTLLM Sampler perf single beam single step (#5550)
|
2025-07-07 15:44:47 +02:00 |
|
kv_cache_transceiver.py
|
feat: Add support for disaggregation with pp with pytorch backend (#6369)
|
2025-07-30 09:42:13 -04:00 |
|
layerwise_nvtx_marker.py
|
Update TensorRT-LLM (#2849)
|
2025-03-04 18:44:00 +08:00 |
|
llm_request.py
|
[TRTLLM-6637][feat] Resolve KV cache divergence issue (#6628)
|
2025-08-09 23:15:04 +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 |
|
model_engine.py
|
[None][feat] CUTLASS MoE FC2+Finalize fusion (#3294)
|
2025-08-12 15:56:48 +08:00 |
|
py_executor_creator.py
|
[None][fix] Refactoring to avoid circular import when importing torch models (#6720)
|
2025-08-11 18:00:42 -04:00 |
|
py_executor.py
|
[None][fix] Fix attention dp log (#6570)
|
2025-08-12 04:53:09 -04:00 |
|
resource_manager.py
|
[None][fix] Refactoring to avoid circular import when importing torch models (#6720)
|
2025-08-11 18:00:42 -04:00 |
|
sampler.py
|
[None][refactor] Simplify decoder state initialization (#6559)
|
2025-08-12 21:44:41 +02:00 |
|
scheduler.py
|
[TRTLLM-6392][feat] Support turning on/off spec decoding dynamically (#6363)
|
2025-07-31 15:31:39 -04:00 |
|
seq_slot_manager.py
|
feat: Optimize TRTLLM Sampler perf single beam single step (#5550)
|
2025-07-07 15:44:47 +02:00 |
