ReleaseNVIDIANVIDIApublished Sep 15, 2025seen Jun 26

NVIDIA/TensorRT-LLM v1.1.0rc2.post2

NVIDIA/TensorRT-LLM

Open original ↗

Captured source

source ↗
GH
GitHub/github.com/NVIDIA/TensorRT-LLM
NVIDIA/TensorRT-LLM v1.1.0rc2.post2
Source ↗
published Sep 15, 2025seen Jun 26captured Sep 1http 200method plain

v1.1.0rc2.post2

Repository: NVIDIA/TensorRT-LLM

Tag: v1.1.0rc2.post2

Published: 2025-09-15T05:11:40Z

Prerelease: yes

Release notes:

Announcement Highlights

  • Feature
  • Add MNNVL AlltoAll tests to pre-merge (#7465)
  • Support multi-threaded tokenizers for trtllm-serve (#7515)
  • FP8 Context MLA integration (#7581)
  • Support block wise FP8 in wide ep (#7423)
  • Cherry-pick Responses API and multiple postprocess workers support for chat harmony (#7600)
  • Make low_precision_combine as a llm arg (#7598)
  • Documentation
  • Update deployment guide and cherry-pick CI test fix from main (#7623)

What's Changed

  • [None] [test] Add MNNVL AlltoAll tests to pre-merge by @kaiyux in https://github.com/NVIDIA/TensorRT-LLM/pull/7465
  • [TRTLLM-7292][feat] Support multi-threaded tokenizers for trtllm-serve by @nv-yilinf in https://github.com/NVIDIA/TensorRT-LLM/pull/7515
  • [None][fix] trtllm-serve yaml loading by @Superjomn in https://github.com/NVIDIA/TensorRT-LLM/pull/7551
  • [None][chore] Bump version to 1.1.0rc2.post2 by @yiqingy0 in https://github.com/NVIDIA/TensorRT-LLM/pull/7582
  • [https://nvbugs/5498967][fix] Downgrade NCCL by @yizhang-nv in https://github.com/NVIDIA/TensorRT-LLM/pull/7556
  • [TRTLLM-6994][feat] FP8 Context MLA integration. by @yuxianq in https://github.com/NVIDIA/TensorRT-LLM/pull/7581
  • [TRTLLM-7831][feat] Support block wise FP8 in wide ep by @xxi-nv in https://github.com/NVIDIA/TensorRT-LLM/pull/7423
  • [None][chore] Make use_low_precision_moe_combine as a llm arg by @zongfeijing in https://github.com/NVIDIA/TensorRT-LLM/pull/7598
  • [None][fix] Update deployment guide and cherry-pick CI test fix from main by @dongfengy in https://github.com/NVIDIA/TensorRT-LLM/pull/7623
  • [None][feat] Cherry-pick Responses API and multiple postprocess workers support for chat harmony by @JunyiXu-nv in https://github.com/NVIDIA/TensorRT-LLM/pull/7600
  • [None][chore] Fix kernel launch param and add TRTLLM MoE backend test by @pengbowang-nv in https://github.com/NVIDIA/TensorRT-LLM/pull/7524

New Contributors

  • @xxi-nv made their first contribution in https://github.com/NVIDIA/TensorRT-LLM/pull/7423

Full Changelog: https://github.com/NVIDIA/TensorRT-LLM/compare/v1.1.0rc2.post1...v1.1.0rc2.post2