| .. |
|
__init__.py
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
_util.py
|
[None][chore] remove executor config in kv cache creator (#7526)
|
2025-09-10 21:14:44 +08:00 |
|
config_utils.py
|
[None][fix] fix hunyuan_moe init bug (#7502)
|
2025-09-04 03:06:00 -04:00 |
|
config.py
|
[None][chore] expose tokens_per_block into KvCacheConfig (#5911)
|
2025-09-07 21:14:10 -04:00 |
|
cuda_graph_runner.py
|
[https://nvbugs/5516666][fix] cherrypick fix to the CUDA graph warmup issue when using speculative decoding (#7737)
|
2025-09-17 06:24:20 +08:00 |
|
executor_request_queue.py
|
[None][opt] Balance the request based on number of tokens in AttentionDP (#7183)
|
2025-08-27 11:16:12 +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-7028][feat] Enable guided decoding with speculative decoding (part 2: one-model engine) (#6948)
|
2025-09-03 15:16:11 -07:00 |
|
guided_decoder.py
|
[TRTLLM-7027][feat] Fuse d2t to logitsBitmaskKernel and fix a race condition in one-model spec (#7481)
|
2025-09-04 23:30:14 +08:00 |
|
handle_logits.py
|
[TRTLLM-7155][feat] Unify sampler handle logits implementation. (#6867)
|
2025-08-22 08:09:30 +02:00 |
|
kv_cache_connector.py
|
[None][chore] add TorchLlmArgs to the connector api (#7493)
|
2025-09-09 09:05:59 -04:00 |
|
kv_cache_transceiver.py
|
[TRTLLM-7361][feat] KV cache transfer for uneven pp (#7117)
|
2025-09-08 13:37:46 -04:00 |
|
layerwise_nvtx_marker.py
|
Update TensorRT-LLM (#2849)
|
2025-03-04 18:44:00 +08:00 |
|
llm_request.py
|
[https://nvbugs/5508536][fix] Revert #7041: Move stop_criteria to sample_async (#7041) (#7796)
|
2025-09-17 21:27:01 -04:00 |
|
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
|
[None] [chore] Mamba cache in separate file (#6796)
|
2025-08-15 13:42:51 +03:00 |
|
model_engine.py
|
[TRTLLM-6994][feat] FP8 Context MLA integration (Cherry-pick https://github.com/NVIDIA/TensorRT-LLM/pull/6059 from release/1.1.0rc2) (#7610)
|
2025-09-19 09:40:49 +08:00 |
|
py_executor_creator.py
|
[TRTLLM-6746][feat] Enable two-model spec dec for MTP Eagle (#7001)
|
2025-09-18 12:05:36 -04:00 |
|
py_executor.py
|
[TRTLLM-6668][feat] Enable overlap scheduler for two-model spec decoding (#7651)
|
2025-09-16 07:33:44 +08:00 |
|
resource_manager.py
|
[https://nvbugs/5480289][fix] release slot manager in mtp MTPHiddenStatesManager (#7340)
|
2025-09-02 19:37:51 -07:00 |
|
sampler.py
|
[https://nvbugs/5508536][fix] Revert #7041: Move stop_criteria to sample_async (#7041) (#7796)
|
2025-09-17 21:27:01 -04:00 |
|
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
|
[https://nvbugs/5394392][fix] Enlarge scheduler capacity under disagg bs == 1 (#6537)
|
2025-08-15 09:52:06 -07:00 |
