HuiGao-NV c51e90d7d7 fix: don't perform memory estimation for start_attention (#3485) ... * fix: don't perform memory estimation for start_attention * Enable tests of unittest/_torch/multi_gpu Signed-off-by: Hui Gao <huig@nvidia.com>		2025-04-12 11:34:46 +08:00
..
__init__.py	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
_util.py	feat: Run PyExecutor's inference flow to estimate max_num_tokens for kv_cache_manager (#3092)	2025-04-10 18:29:40 +08:00
config.py	feat: Optionally split MoE inputs into chunks to reduce GPU memory usage (#3104)	2025-04-01 16:07:02 +08:00
cuda_graph_runner.py	feat: Run PyExecutor's inference flow to estimate max_num_tokens for kv_cache_manager (#3092)	2025-04-10 18:29:40 +08:00
decoder.py	fix the py_decoding_iter update in decoder. (#3297)	2025-04-07 11:18:33 +08:00
distributed.py	Only gather responses on rank 0 (#3040)	2025-03-24 21:54:51 -07:00
guided_decoder.py	Update (#2978)	2025-03-23 16:39:35 +08:00
kv_cache_transceiver.py	Update TensorRT-LLM (#2849)	2025-03-04 18:44:00 +08:00
layerwise_nvtx_marker.py	Update TensorRT-LLM (#2849)	2025-03-04 18:44:00 +08:00
llm_request.py	feat: Run PyExecutor's inference flow to estimate max_num_tokens for kv_cache_manager (#3092)	2025-04-10 18:29:40 +08:00
model_engine.py	feat: Add NVFP4 UB pattern optimization pass in torch compile (#3371)	2025-04-11 21:25:29 +08:00
py_executor_creator.py	fix: don't perform memory estimation for start_attention (#3485)	2025-04-12 11:34:46 +08:00
py_executor.py	feat: Run PyExecutor's inference flow to estimate max_num_tokens for kv_cache_manager (#3092)	2025-04-10 18:29:40 +08:00
resource_manager.py	feat: Support PeftCacheManager in Torch (#3186)	2025-04-04 12:38:08 +08:00
scheduler.py	Update TensorRT-LLM (#2936)	2025-03-18 21:25:19 +08:00