TensorRT-LLMs/tensorrt_llm/_torch/auto_deploy
Lucas Liebenwein 6bf4e59267
[#8763][feature] AutoDeploy: configurable dtype for caching (#8812)
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
2025-11-10 22:17:14 -08:00
..
compile [https://nvbugs/5606166][fix] AutoDeploy: use tuples for cudagraph shape lookup (#8658) 2025-10-28 10:52:43 -07:00
config [TRTLLM-8814][feat] AutoDeploy: Use TRTLLM kernels for FP8 linear (#8820) 2025-11-06 11:00:10 -08:00
custom_ops [#8763][feature] AutoDeploy: configurable dtype for caching (#8812) 2025-11-10 22:17:14 -08:00
distributed [None][fix] Switch AD AllReduce strategy to NCCL (#8979) 2025-11-07 06:49:44 +02:00
export [#8924][fix] Fix AutoDeploy pattern matcher for torch 2.9 (#8920) 2025-11-05 13:29:20 -08:00
models [None][feat] AutoDeploy: Support Latent MOE for Nemotron (#8955) 2025-11-06 12:40:19 -08:00
shim [TRTLLM-9065][chore] remove PyTorchConfig completely (#8856) 2025-11-06 22:37:03 -08:00
transform [#8763][feature] AutoDeploy: configurable dtype for caching (#8812) 2025-11-10 22:17:14 -08:00
utils [https://nvbugs/5625972][fix] Add context manager to fix FakeTensorProp (#9047) 2025-11-10 16:25:58 -08:00
__init__.py [AutoDeploy] merge feat/ad-2025-07-07 (#6196) 2025-07-23 05:11:04 +08:00
llm_args.py [TRTLLM-9065][chore] remove PyTorchConfig completely (#8856) 2025-11-06 22:37:03 -08:00
llm.py [TRTLLM-9065][chore] remove PyTorchConfig completely (#8856) 2025-11-06 22:37:03 -08:00