Mike Iovine 8c2c969fcb [fix] Pad requests to maximum draft length in spec decode (#3957) ... Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>		2025-04-30 11:02:18 -04:00
..
__init__.py	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
_util.py	fix: get head_dim from model’s config. (#3916)	2025-04-29 23:04:29 +08:00
config.py	fix: Fix C++ decoder synchronization in PyTorch (#3106)	2025-04-23 23:55:27 +08:00
cuda_graph_runner.py	Support CUDA graphs for EAGLE3 (#3176)	2025-04-17 04:53:50 +08:00
decoder.py	feat: return logits in PyTorch flow (#3221)	2025-04-24 16:56:03 -07:00
guided_decoder.py	fix: Fix C++ decoder synchronization in PyTorch (#3106)	2025-04-23 23:55:27 +08:00
kv_cache_transceiver.py	cacheTransceiver buffer manager (#3798)	2025-04-27 11:48:15 +08:00
layerwise_nvtx_marker.py	Update TensorRT-LLM (#2849)	2025-03-04 18:44:00 +08:00
llm_request.py	feat: return logits in PyTorch flow (#3221)	2025-04-24 16:56:03 -07:00
model_engine.py	[fix] Pad requests to maximum draft length in spec decode (#3957)	2025-04-30 11:02:18 -04:00
py_executor_creator.py	Add running E2E LoRA flow (#3648)	2025-04-23 11:19:41 +08:00
py_executor.py	[fix] Pad requests to maximum draft length in spec decode (#3957)	2025-04-30 11:02:18 -04:00
resource_manager.py	chore: remove DummyKvCacheManager. (#3896)	2025-04-29 09:59:37 +08:00
scheduler.py	refactor: collect executor and decoder states into dataclass (#3234)	2025-04-15 16:31:45 +08:00
seq_slot_manager.py	fix: Fix C++ decoder synchronization in PyTorch (#3106)	2025-04-23 23:55:27 +08:00