Lucas Liebenwein 9879400479 [#10642][feat] AutoDeploy: optimized canonicalize_graph utilities [1/2] (#10675) ... Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>		2026-01-18 13:42:30 -05:00
..
compile	[None][feat] AutoDeploy: prepare_metadata revisited (#9764)	2025-12-12 20:14:14 +08:00
config	[None][fix] AutoDeploy: Fix the nvfp4 fused_moe (#10727)	2026-01-16 12:04:40 -08:00
custom_ops	[#10696][fix] AutoDeploy prevent torch.export from specializing batch dimension when max_batch_size=1 (#10697)	2026-01-18 10:42:49 +02:00
distributed	[None][refactor] Unify the usage of MPIDist and TorchDist. (#10380)	2026-01-14 14:05:47 +08:00
export	[https://nvbugs/5732942][fix] AutoDeploy: handle transformers 4.57.1 upgrade fixes (#10466)	2026-01-06 19:55:49 -05:00
models	[None][fix] AutoDeploy: Fix the nvfp4 fused_moe (#10727)	2026-01-16 12:04:40 -08:00
shim	[None][feat] Auto download speculative models from HF for pytorch backend, add speculative_model field alias (#10099)	2026-01-14 21:06:07 -08:00
transform	[#10642][feat] AutoDeploy: optimized canonicalize_graph utilities [1/2] (#10675)	2026-01-18 13:42:30 -05:00
utils	[#10642][feat] AutoDeploy: optimized canonicalize_graph utilities [1/2] (#10675)	2026-01-18 13:42:30 -05:00
__init__.py	[AutoDeploy] merge feat/ad-2025-07-07 (#6196)	2025-07-23 05:11:04 +08:00
llm_args.py	[#10688][fix] AutoDeploy Fix CUDA graph batch sizes exceeding max_batch_size (#10687)	2026-01-18 13:31:01 -05:00
llm.py	[TRTLLM-9065][chore] remove PyTorchConfig completely (#8856)	2025-11-06 22:37:03 -08:00