Grzegorz Kwasniewski 0d1f5ad7a2 [TRTLLM-10358][feat] Added proper rescaling of FP4 weights (#10378) ... Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>		2026-01-03 16:26:16 -05:00
..
compile	[None][feat] AutoDeploy: prepare_metadata revisited (#9764)	2025-12-12 20:14:14 +08:00
config	[#9626][feat] Add an auto-deploy transform for using cutlass FP4 MoE kernels (#10304)	2025-12-29 23:18:15 +02:00
custom_ops	[#10244][feat] AutoDeploy: separate prefill/decode in flashinfer (#10252)	2025-12-31 17:01:24 -05:00
distributed	[#9198][feat] Refactor dist ops in AutoDeploy (#9301)	2025-12-02 02:36:32 +08:00
export	[#9230][feat] Slimmed down implementation of nemotron H (#9235)	2025-11-23 03:13:32 -08:00
models	[#10056][chore] AutoDeploy: Enable Nemo SuperV3 accuracy test (#10308)	2026-01-02 11:20:19 +02:00
shim	[#10244][feat] AutoDeploy: separate prefill/decode in flashinfer (#10252)	2025-12-31 17:01:24 -05:00
transform	[#10056][fix] AutoDeploy: Handle deletion of nested params in sharding (#10376)	2026-01-01 08:11:11 -05:00
utils	[TRTLLM-10358][feat] Added proper rescaling of FP4 weights (#10378)	2026-01-03 16:26:16 -05:00
__init__.py	[AutoDeploy] merge feat/ad-2025-07-07 (#6196)	2025-07-23 05:11:04 +08:00
llm_args.py	[#9241][feat] AutoDeploy: Support Eagle3 Speculative Decoding (#9869)	2025-12-24 23:30:42 -05:00
llm.py	[TRTLLM-9065][chore] remove PyTorchConfig completely (#8856)	2025-11-06 22:37:03 -08:00