Yechan Kim 67208f1512 [None][fix] InputProcessor config naming convention fix (#8705) ... Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>		2025-11-03 22:29:21 -08:00
..
compile	[https://nvbugs/5606166][fix] AutoDeploy: use tuples for cudagraph shape lookup (#8658)	2025-10-28 10:52:43 -07:00
config	[None][feat] AutoDeploy: Add FP8 MOE for Nemotron (#8599)	2025-10-25 15:26:45 -04:00
custom_ops	[None][perf] AutoDeploy optimize _get_unique_value (#8822)	2025-10-31 04:57:10 -07:00
distributed	[#8781][fix] Cache the AllReduce wrapper to avoid re-allocating workspace which caused a hang (#8803)	2025-11-02 15:30:39 +02:00
export	[#4585][feat] Replace unified attention before export (#8303)	2025-10-23 18:02:04 -04:00
models	[#8245][feat] Autodeploy: Guided Decoding Support (#8551)	2025-10-28 09:29:57 +08:00
shim	[TRTLLM-8836][chore] Create ModelEngine from LlmArgs (#8600)	2025-11-01 05:26:06 -07:00
transform	[TRTLLM-8734][feat] AutoDeploy: Enable the nvfp4 for Nemotron MOE (#8737)	2025-10-30 12:33:08 -07:00
utils	[None][chore] AutoDeploy: cleanup old inference optimizer configs (#8039)	2025-10-17 15:55:57 -04:00
__init__.py	[AutoDeploy] merge feat/ad-2025-07-07 (#6196)	2025-07-23 05:11:04 +08:00
llm_args.py	[TRTLLM-8684][chore] Migrate BuildConfig to Pydantic, add a Python wrapper for KVCacheType enum (#8330)	2025-10-28 09:17:26 -07:00
llm.py	[None][fix] InputProcessor config naming convention fix (#8705)	2025-11-03 22:29:21 -08:00