kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
8444a50d3a
TensorRT-LLMs/tensorrt_llm/_torch/auto_deploy
History
Lucas Liebenwein 22aa4ac08c
[None][feat] AutoDeploy: VLMs with subgraphs + cudagraph/compile (#8203) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
2025-10-13 17:34:09 -07:00
..
compile [None][feat] AutoDeploy: compiler backends based on nn.Module (#8126) 2025-10-03 12:14:21 -04:00
config [None][feat] AutoDeploy: VLMs with subgraphs + cudagraph/compile (#8203) 2025-10-13 17:34:09 -07:00
custom_ops [None][feat] AutoDeploy: VLMs with subgraphs + cudagraph/compile (#8203) 2025-10-13 17:34:09 -07:00
distributed [TRTLLM-7349][feat] Adding new orchestrator type -- ray (#7520) 2025-10-04 08:12:24 +08:00
export [None][feat] AutoDeploy: VLMs with subgraphs + cudagraph/compile (#8203) 2025-10-13 17:34:09 -07:00
models [None][feat] AutoDeploy: VLMs with subgraphs + cudagraph/compile (#8203) 2025-10-13 17:34:09 -07:00
shim [None][feat] AutoDeploy: VLMs with subgraphs + cudagraph/compile (#8203) 2025-10-13 17:34:09 -07:00
transform [None][feat] AutoDeploy: VLMs with subgraphs + cudagraph/compile (#8203) 2025-10-13 17:34:09 -07:00
transformations [None][feat] AutoDeploy: VLMs with subgraphs + cudagraph/compile (#8203) 2025-10-13 17:34:09 -07:00
utils [TRTLLM-6342][feat] Factory TP sharding of quantized models (#8123) 2025-10-13 14:04:46 -07:00
__init__.py [AutoDeploy] merge feat/ad-2025-07-07 (#6196) 2025-07-23 05:11:04 +08:00
llm_args.py [None][feat] AutoDeploy: dive deeper into token generation bugs + enable_block_reuse (#8108) 2025-10-03 04:57:26 -07:00
llm.py [#4593][feat] AutoDeploy: Linear Attention Support (SSM + causal_conv + Bamba + Nemotron-H) (#8068) 2025-09-29 22:41:06 -04:00