Let decode_chunk_size be tuned per quantizer like block_chunk_size

9a6ce16

Select commit

Loading

Failed to load commit list.

Uh oh!

There was an error while loading. Please reload this page.

DCO

Codecov

codecov/project

Unit tests on: pull_request 19

check-file-changes

linux

windows

multi-version (unit-3.10(torch_214, tf_latest), 3.10)

multi-version (unit-3.11(torch_214, tf_latest), 3.11)

multi-version (unit-3.13(torch_214, tf_latest), 3.13)

multi-version (unit-3.14(torch_214, tf_latest), 3.14)

multi-version (unit-3.12(torch_28, tf_latest), 3.12)

multi-version (unit-3.12(torch_29, tf_latest), 3.12)

multi-version (unit-3.12(torch_210, tf_latest), 3.12)

multi-version (unit-3.12(torch_211, tf_latest), 3.12)

multi-version (unit-3.12(torch_212, tf_latest), 3.12)

multi-version (unit-3.12(torch_213, tf_latest), 3.12)

multi-version (unit-3.12(torch_214, tf_min), 3.12)

partial-install (onnx)

partial-install (torch)

launcher

mcp

skills

unit-pr-required-check

Docs on: pull_request 4

build-docs

changes

deploy-gh-pages

deploy-preview

Code Quality on: pull_request 1

code-quality

Claude on: pull_request_review

Claude (interactive)

Regression tests on: push 3

pr-gate / check-file-changes

pr-gate / wait-checks

regression-tests

regression-pr-required-check

Example tests on: push 2

pr-gate

torch (llm_distill) / run-test

torch (llm_qat) / run-test

torch (llm_sparsity) / run-test

torch (specdec_bench) / run-test

torch (speculative_decoding) / run-test

torch (vllm_serve) / run-test

trtllm (gpt-oss) / run-test

trtllm (hf_ptq) / run-test

trtllm (llm_eval) / run-test

megatron / run-test

onnx (diffusers) / run-test

onnx (torch_onnx) / run-test

onnx (torch_trt) / run-test

example-pr-required-check

GPU tests on: push 3

pr-gate / check-file-changes

pr-gate / wait-checks

gpu-tests (gpu, 60, nvcr.io/nvidia/pytorch:26.05-py3)

gpu-tests (gpu_megatron, 60, nvcr.io/nvidia/nemo:26.08)

gpu-tests (gpu_trtllm, 15, nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc20)

gpu-tests (gpu_vllm, 15, docker.io/vllm/vllm-openai:v0.26.0)

gpu-tests (gpu_vllm, 15, docker.io/vllm/vllm-openai:v0.20.0)

gpu-pr-required-check

Docs on: pull_request 2

build-docs

changes

deploy-gh-pages

deploy-preview

DCO / DCO succeeded Sep 22, 2026 in 1s

DCO

All commits are signed off!

View more details on DCO

Loading

Let decode_chunk_size be tuned per quantizer like block_chunk_size

Uh oh!

DCO

Re-running checks...