[Misc] Remove unused `executor.apply_model` (#26215)

Cyrus Leung committed about 1 year ago

[Misc] Require `merge_by_field_config` argument (#26214)

Cyrus Leung committed about 1 year ago

[Model] Support nested structures for TensorSchema (#26212)

Cyrus Leung committed about 1 year ago

Support expert parallel in Transformers backend (#26162)

Harry Mellor committed about 1 year ago

[V1] [Hybrid] Mamba2 Automatic Prefix Caching (#25752)

Stan Wozniak committed about 1 year ago

[cpu][perf] Accelerate unquantized-linear for AArch64 through oneDNN/ACL and weight prepack (#25948)

Fadi Arafeh committed about 1 year ago

Add batch invariant kernel override for FlashInfer backend [2/n] (#25769)

Bram Wasti committed about 1 year ago

[BugFix] Use async Mistral Tokenizer in Chat Completions (#26134)

Ben Browning committed about 1 year ago

[Bugfix] Fix qwen3 vl dummy data generation with overrides (#26193)

Roger Wang committed about 1 year ago

Fix issue of using only the part of video frame [Nemotron Nano] (#26186)

Eugene Khvedchenya committed about 1 year ago

[GPTOSS][DP/EP][Marlin] Enable GPTOSS DP/EP using Marlin kernels (#25488)

Varun Sundar Rabindranath committed about 1 year ago

[CI] Fix Pre-commit Mypy Error (#26181)

Wentao Ye committed about 1 year ago

[BugFix] Fix de-functionalization pass for rotary_embedding (#23953)

Angela Yi committed about 1 year ago

[Misc] Add penalties sampling parameters to serve tool (#25974)

Sergei Skvortsov committed about 1 year ago

[CI] Push multiarch manifests as nightly builds (#25764)

Sahithi Chigurupati committed about 1 year ago

[Bugfix] Relax tokenizer regex for mixtral to include 'tokenizer.model' (#25964)

Bowen Bao committed about 1 year ago

[responsesAPI] add better error messaging for long prompts (#25724)

Andrew Xia committed about 1 year ago

[Refactor] Optimize FP8 MOE Backend Choice and Log (#26044)

Wentao Ye committed about 1 year ago

[Perf] Remove hardcoded num_warps=1 (#26183)

Corey Lowman committed about 1 year ago

[Quantization/NVFP4] Speed up TRTLLM NVFP4 MOE weight loading and fix K/V scale loading for MLA Attn (#25968)

Pavani Majety committed about 1 year ago