| .. |
|
__init__.py
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
_util.py
|
[fix] Add 1 and draft_token_num to seq_len when overlap scheduling is enabled during memory estimation (#5343)
|
2025-06-24 11:43:43 +08:00 |
|
config_utils.py
|
feat: support kv cache reuse for MLA (#3571)
|
2025-05-15 15:22:21 +08:00 |
|
config.py
|
feat: Support stream_interval (#5284)
|
2025-06-19 21:57:10 +08:00 |
|
cuda_graph_runner.py
|
[TRTLLM-4983] feat: enable overlap scheduler between draft forwards (#4802)
|
2025-06-15 23:09:16 +08:00 |
|
grammar_matcher.py
|
feat: Add LLGuidance Support for PyTorch Backend (#5214)
|
2025-06-18 19:33:34 +08:00 |
|
guided_decoder.py
|
feature: unify new_tokens format sample state to trtllm sampler new_tokens format (#4401)
|
2025-06-23 10:38:37 -07:00 |
|
handle_context_logits.py
|
refactor: Update decoder buffer and logits management (#4450)
|
2025-06-18 08:10:32 +08:00 |
|
handle_generation_logits.py
|
refactor: Update decoder buffer and logits management (#4450)
|
2025-06-18 08:10:32 +08:00 |
|
kv_cache_transceiver.py
|
Solve underallocation in VSWA+/VGQA (#4667)
|
2025-06-12 12:12:46 +08:00 |
|
layerwise_nvtx_marker.py
|
Update TensorRT-LLM (#2849)
|
2025-03-04 18:44:00 +08:00 |
|
llm_request.py
|
feature: unify new_tokens format sample state to trtllm sampler new_tokens format (#4401)
|
2025-06-23 10:38:37 -07:00 |
|
make_decoding_batch_input_output.py
|
refactor: manage cache indirection in decoder state (#5315)
|
2025-06-24 09:15:59 +02:00 |
|
model_engine.py
|
feature: unify new_tokens format sample state to trtllm sampler new_tokens format (#4401)
|
2025-06-23 10:38:37 -07:00 |
|
py_executor_creator.py
|
refactor: Introduce ResourceManagerType enum for resource management (#5246)
|
2025-06-18 09:55:59 +02:00 |
|
py_executor.py
|
feature: unify new_tokens format sample state to trtllm sampler new_tokens format (#4401)
|
2025-06-23 10:38:37 -07:00 |
|
resource_manager.py
|
refactor: Introduce ResourceManagerType enum for resource management (#5246)
|
2025-06-18 09:55:59 +02:00 |
|
sampler.py
|
refactor: manage cache indirection in decoder state (#5315)
|
2025-06-24 09:15:59 +02:00 |
|
scheduler.py
|
feature: unify new_tokens format sample state to trtllm sampler new_tokens format (#4401)
|
2025-06-23 10:38:37 -07:00 |
|
seq_slot_manager.py
|
feature: unify new_tokens format sample state to trtllm sampler new_tokens format (#4401)
|
2025-06-23 10:38:37 -07:00 |
