HuiGao-NV f4059c6e2e Add test case for kv memory estimation (#4158) ... * Add test case for kv memory estimation * Dump running log into file and parse kv cache memory size from file * Set bigger peak memory size for mixed percision case and test_ptp_quickstart_advanced_eagle3 case * Revert change to usage of fraction * use context manager to guard temp files Signed-off-by: Hui Gao <huig@nvidia.com>		2025-05-14 18:39:25 +08:00
..
__init__.py	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
_util.py	Add test case for kv memory estimation (#4158)	2025-05-14 18:39:25 +08:00
config.py	[TRTLLM-5050][feat] Enable per-request stats with PyT backend (#4156)	2025-05-12 21:35:15 -04:00
cuda_graph_runner.py	[TRTLLM-3105][feat] Add Piecewise CUDA Graph Support (#3804)	2025-05-09 11:04:01 +08:00
decoder.py	feat: adopt new logprob definition in PyTorch flow (#4057)	2025-05-08 20:16:40 +08:00
guided_decoder.py	feat: Support the Structural Tag in guided decoding (#4066)	2025-05-12 17:24:50 +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: adopt new logprob definition in PyTorch flow (#4057)	2025-05-08 20:16:40 +08:00
model_engine.py	feat: Prefetch safetensors files before loading them (#4140)	2025-05-13 13:35:30 +08:00
py_executor_creator.py	fix: [https://nvbugspro.nvidia.com/bug/5238626] illegal memory address when running llama 4 with cuda graph enabled (#4101)	2025-05-13 14:58:54 +08:00
py_executor.py	fix: Merge PP overlap and non-overlap executor loop (#3878)	2025-05-14 06:04:36 +08:00
resource_manager.py	[fix] Fix add_dummy_requests for spec decoding cases (#4084)	2025-05-09 16:52:51 +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: skip add new slot if request has slot 0 (#3991)	2025-05-06 07:46:39 +02:00