[1/N] Initial vllm-ext evaluation support (MXFP4 MOE) #935

yiliu30 · 2025-10-23T02:35:50Z

Usage

source apply_ext.sh 
VLLM_ENABLE_AR_EXT=1 vllm serve ...

Initial support for out-of-tree AutoRound integration with vLLM, verified on Qwen3-15B-A2B-Base.

Added AutoRoundExtensionConfig
Monkey patching support
Added AutoRoundMoEMethod and AutoRoundMoEMethodMXFp4Impl
UT

There are three paths for MXFP4

VLLM_ENABLE_STATIC_MOE=1: static MOE + unpack the weight on the fly, very slow, for correctness check
VLLM_ENABLE_STATIC_MOE=1 + VLLM_MXFP4_PRE_UNPACK_WEIGHTS=1, static MOE + unpack the weight to FP8 before inference, still slow but acceptable
VLLM_AR_MXFP4_MODULAR_MOE=1 + VLLM_MXFP4_PRE_UNPACK_WEIGHTS=1, unpack the weight to BF16 + FP32 group gemm, fast but requires the same mem as BF16 models, WIP, support it in the next PR

Signed-off-by: yiliu30 <[email protected]>

auto_round_extension/vllm_ext/tests/conftest.py

Copilot

Pull Request Overview

This PR introduces initial support for out-of-tree AutoRound integration with vLLM, specifically for MXFP4 MOE quantization. The implementation adds extension configuration, MOE quantization methods, and utilities for FP4/MXFP4 quantization and dequantization operations.

Key changes:

Added AutoRoundExtensionConfig to extend AutoRound's quantization support with MXFP4 MOE capabilities
Implemented AutoRoundMoEMethod and AutoRoundMoEMethodMXFp4Impl for handling MOE layers with MXFP4 quantization
Created utility modules for MXFP4 quantization/dequantization, FP4 conversions, and environment variable extensions

Reviewed Changes

Copilot reviewed 11 out of 11 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
auto_round/experimental/vllm_ext/utils.py	MXFP4 scale derivation and quantization utilities for E8M0 exponent handling
auto_round/experimental/vllm_ext/tests/test_mxfp4_moe.py	Basic test validating AutoRound MXFP4 model inference
auto_round/experimental/vllm_ext/tests/conftest.py	Test fixtures and runners copied from vLLM
auto_round/experimental/vllm_ext/sitecustomize.py	Bootstrap script for enabling AutoRound extension via environment variable
auto_round/experimental/vllm_ext/quant_method_moe.py	MOE quantization method dispatcher for AutoRound
auto_round/experimental/vllm_ext/mxfp4_qdq_utils.py	MXFP4 quantization/dequantization implementation
auto_round/experimental/vllm_ext/moe_impl_mxfp4.py	MXFP4 MOE layer implementation with weight processing
auto_round/experimental/vllm_ext/fp4_utils.py	FP4 E2M1 format packing/unpacking utilities
auto_round/experimental/vllm_ext/envs_ext.py	Extension environment variables for MXFP4 configuration
auto_round/experimental/vllm_ext/auto_round_ext.py	AutoRound extension configuration class
auto_round/experimental/vllm_ext/init.py	Extension application entry point

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

auto_round_extension/vllm_ext/auto_round_ext.py

auto_round_extension/vllm_ext/tests/test_mxfp4_moe.py

auto_round_extension/vllm_ext/mxfp4_qdq_utils.py

Signed-off-by: yiliu30 <[email protected]>

auto_round/experimental/vllm_ext/fp4_utils.py

Signed-off-by: yiliu30 <[email protected]>

auto_round_extension/vllm_ext/tests/conftest.py

Signed-off-by: yiliu30 <[email protected]>

…llm-ext

auto_round_extension/vllm_ext/__init__.py

Signed-off-by: yiliu30 <[email protected]>

auto_round_extension/vllm_ext/utils.py

auto_round_extension/vllm_ext/quant_method_moe.py

auto_round_extension/vllm_ext/moe_impl_mxfp4.py

auto_round_extension/vllm_ext/fp4_utils.py

Signed-off-by: yiliu30 <[email protected]>

wenhuach21 · 2025-10-30T01:55:24Z

I’m not very familiar with this part. @mengniwang95 @n1ck-guo, could you please review it again and approve the PR if everything looks good?

auto_round_extension/vllm_ext/moe_impl_mxfp4.py

Signed-off-by: yiliu30 <[email protected]>

* Fix rtn tuning_device issue (#893) Signed-off-by: Kaihui-intel <[email protected]> * fix vlm gguf ut (#895) Signed-off-by: n1ck-guo <[email protected]> * update alg_ext.abi3.so with python compatible version (#894) * move ste from quant to round for nvfp4 (#889) Signed-off-by: He, Xin3 <[email protected]> * Add GPT-OSS quant support (#887) * better help printing information (#883) * better help printing information Signed-off-by: n1ck-guo <[email protected]> * speedup quant and evaluation, fix recompile issue (#897) * rewrite the implementation for ease-of-maintain Signed-off-by: He, Xin3 <[email protected]> * fix bug Signed-off-by: He, Xin3 <[email protected]> * fix quant performance Signed-off-by: He, Xin3 <[email protected]> * Update auto_round/compressors/base.py --------- Signed-off-by: He, Xin3 <[email protected]> * fix nvfp act quantization bug (#891) * fix nvfp act quantization bug Signed-off-by: Zhang, Weiwei1 <[email protected]> * add cuda ut for moe nvfp quantize Signed-off-by: Zhang, Weiwei1 <[email protected]> * add cpu UT, refine cuda UT Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix ut typo Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix cpu ut Signed-off-by: Zhang, Weiwei1 <[email protected]> * enhance experts amax match, refine UT Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Signed-off-by: Zhang, Weiwei1 <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * support automatic mixed bits assignment (#851) * try to fix gguf issue (#886) * remove numba from requirments (#905) Signed-off-by: yiliu30 <[email protected]> * Extend mxfp loading dtypes (#907) * block dataset logger info (#908) Signed-off-by: n1ck-guo <[email protected]> * fix torch compile issue in AutoScheme (#909) * Revert "Extend mxfp loading dtypes (#907)" (#915) This reverts commit 0c2619c. * support disable_opt_rtn in auto-scheme (#913) * fix llama 4 ut (#896) * fix ut of llama 4 Signed-off-by: n1ck-guo <[email protected]> * add numba for cpu lib (#919) Signed-off-by: yiliu30 <[email protected]> * Loosen the packing restrictions for mxfp&nvfp (#911) * Loosen the packing restrictions for mxfp&nvfp, enable Qwen1.5-MoE-A2.7B quantize Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix UT Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refine mxfp&nvfp layer checker Signed-off-by: Zhang, Weiwei1 <[email protected]> * fix pylint Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Signed-off-by: Zhang, Weiwei1 <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Extend mxfp loading dtypes (#916) Signed-off-by: root <[email protected]> Signed-off-by: yiliu30 <[email protected]> Co-authored-by: root <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fix act config exporting for mixed schemes (#903) * fp8 exporting bugfix Signed-off-by: Zhang, Weiwei1 <[email protected]> * fix act related config saving Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add ut for act_config check Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refine extra_config saving, add UTs Signed-off-by: Zhang, Weiwei1 <[email protected]> * fix ut typo Signed-off-by: Zhang, Weiwei1 <[email protected]> * fix ut typo Signed-off-by: Zhang, Weiwei1 <[email protected]> * fixtypo Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix CI Signed-off-by: Zhang, Weiwei1 <[email protected]> * fix scan issue Signed-off-by: Zhang, Weiwei1 <[email protected]> * fix scan issue Signed-off-by: Zhang, Weiwei1 <[email protected]> * rm global variable Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * rerun ut Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refine ut Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Signed-off-by: Zhang, Weiwei1 <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * optimize rtn for int woq (#924) * fix bug of gguf and support for LiquidAI/LFM2-1.2B (#927) Signed-off-by: n1ck-guo <[email protected]> * remove numpy<2.0 limitation (#921) * enable regex quantization config saving for mixed bits (#825) * enable dynamic quantization config saving Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fixtypo Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * rebase code, refine config saving Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refine ut Signed-off-by: Zhang, Weiwei1 <[email protected]> * fix UT Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * enable hf loading for regex, add UTs Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refine export, enhance gptq UT Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Signed-off-by: Zhang, Weiwei1 <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fix Flux tuning issue (#936) Signed-off-by: Mengni Wang <[email protected]> * gguf support for inclusionAI/Ling-flash-2.0 (#940) * remove low_cpu_mem (#934) * Add compatibility test (#918) * Add commit hash to version (#941) Signed-off-by: Sun, Xuehao <[email protected]> * gguf weight type align with original, output.weight, token_embed (#900) * support attention mask in user's dataset (#930) * Add diffusion README (#923) * update readme (#949) * refactor utils file (#943) * refact utils Signed-off-by: n1ck-guo <[email protected]> * update readme for sglang support (#953) * update readme for sglang support Signed-off-by: Zhang, Weiwei1 <[email protected]> * refine doc Signed-off-by: Zhang, Weiwei1 <[email protected]> * Update README.md --------- Signed-off-by: Zhang, Weiwei1 <[email protected]> Co-authored-by: Wenhua Cheng <[email protected]> * update gguf and support for CompressedLinear (#950) * Reduce AutoSchem VRAM usage by up to 10X (#944) * add self attribution and fix avg_bits error (#956) * add self attribution and fix avg_bits error --------- Signed-off-by: He, Xin3 <[email protected]> Co-authored-by: Wenhua Cheng <[email protected]> * add logo (#960) * refine AutoScheme readme/code (#958) * update readme (#962) * fix critic disable_opt_rtn regression (#963) * [1/N] Initial vllm-ext evaluation support (MXFP4 MOE) (#935) Signed-off-by: yiliu30 <[email protected]> * fix bug of imatrix contains 0 (#955) * fix rtn bug (#966) * enhance flux doc (#967) * clean code (#968) * support for model scope (#957) * support for model scope Signed-off-by: n1ck-guo <[email protected]> * merge main branch to alg_ext (#970) * fix cuda CI backend issue, fixtypo (#974) * disable compile packing by default (#975) Signed-off-by: yiliu30 <[email protected]> * enhance auto device map and support XPU (#961) * enhance auto device map and support XPU --------- Signed-off-by: He, Xin3 <[email protected]> * refine readme (#978) * cli support for positional arguments model (#979) Signed-off-by: n1ck-guo <[email protected]> * update bits (#986) Signed-off-by: He, Xin3 <[email protected]> * fix guff scheme and device_map bug (#969) * add support for Magistral-Small (#980) * support model_dtype and fix bug of scheme contains quotes, mllm eval (#985) --------- Signed-off-by: Kaihui-intel <[email protected]> Signed-off-by: n1ck-guo <[email protected]> Signed-off-by: He, Xin3 <[email protected]> Signed-off-by: Zhang, Weiwei1 <[email protected]> Signed-off-by: yiliu30 <[email protected]> Signed-off-by: root <[email protected]> Signed-off-by: Mengni Wang <[email protected]> Signed-off-by: Sun, Xuehao <[email protected]> Co-authored-by: Tang Kaihui <[email protected]> Co-authored-by: Heng Guo <[email protected]> Co-authored-by: Xin He <[email protected]> Co-authored-by: Yi Liu <[email protected]> Co-authored-by: Weiwei <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Wenhua Cheng <[email protected]> Co-authored-by: root <[email protected]> Co-authored-by: Wang, Mengni <[email protected]> Co-authored-by: Sun, Xuehao <[email protected]>

init moe support

5ee2c2d

Signed-off-by: yiliu30 <[email protected]>

yiliu30 changed the title ~~init moe support~~ [1/N] Initial vllm-ext evaluation support (MXFP4 MOE) Oct 23, 2025

add test

c278f9d

Signed-off-by: yiliu30 <[email protected]>

github-advanced-security bot found potential problems Oct 23, 2025

View reviewed changes

auto_round_extension/vllm_ext/tests/conftest.py Fixed Show fixed Hide fixed

yiliu30 requested a review from Copilot October 23, 2025 02:42

Copilot AI reviewed Oct 23, 2025

View reviewed changes

auto_round_extension/vllm_ext/auto_round_ext.py Show resolved Hide resolved

auto_round_extension/vllm_ext/tests/test_mxfp4_moe.py Outdated Show resolved Hide resolved

auto_round_extension/vllm_ext/mxfp4_qdq_utils.py Outdated Show resolved Hide resolved

yiliu30 added 4 commits October 22, 2025 22:45

fix import

418e6a0

Signed-off-by: yiliu30 <[email protected]>

clean envs

184783f

Signed-off-by: yiliu30 <[email protected]>

add script for apply ext

b9da06f

Signed-off-by: yiliu30 <[email protected]>

clean docs

187f38d

Signed-off-by: yiliu30 <[email protected]>

yiliu30 requested review from XuehaoSun, mengniwang95 and wenhuach21 October 23, 2025 02:57

yiliu30 marked this pull request as ready for review October 23, 2025 03:05

yiliu30 mentioned this pull request Oct 23, 2025

MXFP4/MXFP8 evaluation #937

Open

5 tasks

mengniwang95 reviewed Oct 23, 2025

View reviewed changes

auto_round/experimental/vllm_ext/fp4_utils.py Outdated Show resolved Hide resolved

yiliu30 added 2 commits October 23, 2025 02:35

fix license

4031724

Signed-off-by: yiliu30 <[email protected]>

fix

5fe01ef

Signed-off-by: yiliu30 <[email protected]>

yiliu30 requested review from mengniwang95 and n1ck-guo October 23, 2025 08:11

yiliu30 added 2 commits October 23, 2025 06:35

fix import and sitecustomize

73f1e9b

Signed-off-by: yiliu30 <[email protected]>

move to ext

8495854

Signed-off-by: yiliu30 <[email protected]>

github-advanced-security bot found potential problems Oct 24, 2025

View reviewed changes

auto_round_extension/vllm_ext/tests/conftest.py Dismissed Show dismissed Hide dismissed

yiliu30 added 6 commits October 24, 2025 04:04

update mxfp4

c473934

Signed-off-by: yiliu30 <[email protected]>

fix

9f65bd1

Signed-off-by: yiliu30 <[email protected]>

fix model name

8038a5f

Signed-off-by: yiliu30 <[email protected]>

Merge branch 'main' into vllm-ext

e0872b6

fix

c82bce1

Signed-off-by: yiliu30 <[email protected]>

Merge branch 'vllm-ext' of https://github.com/intel/auto-round into v…

19e18c7

…llm-ext

n1ck-guo reviewed Oct 27, 2025

View reviewed changes

auto_round_extension/vllm_ext/__init__.py Outdated Show resolved Hide resolved

yiliu30 added 2 commits October 27, 2025 02:22

use absolute path

adf7ebf

Signed-off-by: yiliu30 <[email protected]>

Merge branch 'main' into vllm-ext

59f5cd2

n1ck-guo reviewed Oct 27, 2025

View reviewed changes

auto_round_extension/vllm_ext/utils.py Show resolved Hide resolved

wenhuach21 reviewed Oct 27, 2025

View reviewed changes

auto_round_extension/vllm_ext/quant_method_moe.py Show resolved Hide resolved

mengniwang95 reviewed Oct 27, 2025

View reviewed changes

auto_round_extension/vllm_ext/moe_impl_mxfp4.py Outdated Show resolved Hide resolved

mengniwang95 reviewed Oct 27, 2025

View reviewed changes

auto_round_extension/vllm_ext/fp4_utils.py Outdated Show resolved Hide resolved

yiliu30 added 2 commits October 29, 2025 20:45

Merge branch 'main' into vllm-ext

8f27041

Signed-off-by: yiliu30 <[email protected]>

fix

ad8537c

Signed-off-by: yiliu30 <[email protected]>

yiliu30 requested review from mengniwang95, n1ck-guo and wenhuach21 October 30, 2025 00:55

mengniwang95 reviewed Oct 30, 2025

View reviewed changes

auto_round_extension/vllm_ext/moe_impl_mxfp4.py Show resolved Hide resolved

mark round method as todo

77844f6

Signed-off-by: yiliu30 <[email protected]>

mengniwang95 approved these changes Oct 30, 2025

View reviewed changes

yiliu30 merged commit e8bc353 into main Oct 30, 2025
21 checks passed

yiliu30 deleted the vllm-ext branch October 30, 2025 07:22

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[1/N] Initial vllm-ext evaluation support (MXFP4 MOE) #935

[1/N] Initial vllm-ext evaluation support (MXFP4 MOE) #935

Uh oh!

yiliu30 commented Oct 23, 2025 •

edited

Loading

Uh oh!

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

wenhuach21 commented Oct 30, 2025

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

[1/N] Initial vllm-ext evaluation support (MXFP4 MOE) #935

[1/N] Initial vllm-ext evaluation support (MXFP4 MOE) #935

Uh oh!

Conversation

yiliu30 commented Oct 23, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Usage

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull Request Overview

Reviewed Changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

wenhuach21 commented Oct 30, 2025

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

yiliu30 commented Oct 23, 2025 •

edited

Loading