Hacktoberfest 2026:维护者为十月标记出来的 issue,仍然开放、适合新手。 浏览 Hacktoberfest issue

Apple Silicon MPS: official FL2VA ComfyUI INT8 path fails on aten::_int_mm

未关闭
#56 3 条评论 3 个 reaction 已指派 0 人 在 GitHub 查看

还没有人认领这个 Issue。

评估

难度
5/5
预计耗时
一周以上
新手友好度
35/100
Issue 类型
缺陷
描述清晰度
需要澄清
活跃度
活跃
技术栈
python, pytorch

调研方向

首先,在 MPS 上使用官方 INT8 ComfyUI 路径复现原生 T2VA 工作流,并记录 comfy_kitchen DiT ConvRot 路径中的 aten::_int_mm 失败。检查该限制属于 PyTorch MPS 还是量化集成,然后确定受支持的 Apple Silicon 路径,或记录其不受支持。完成标准是实现可正常工作的本地生成,或明确且经过验证的支持限制。

由索引模型根据 Issue 内容生成。

描述

Local validation report — H3 FL2VA on Apple Silicon

Status

Blocked for a functional local generation through the official quantized ComfyUI path. Installation and model loading succeed; sampling fails on the first iteration because an MPS operator is unavailable.

Machine

Mac Studio Mac14,14 — Apple M2 Ultra, 24 CPU, 60 GPU, 64 GB unified memory, Metal 4, macOS 26.5.2.

Tested backend

ComfyUI stock 0.33.0 + PyTorch 2.13.0 + MPS, with no additional H3 custom node and no Sage Attention. Outside the sandbox, mps_available=True and ComfyUI detects Device: mps.

Models
  • minimax_h3_fl2va_pruned_int8_convrot.safetensors — ~20 GiB
  • qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors — ~15 GiB
  • Video VAE — ~4.8 GiB
  • Audio VAE — ~577 MiB

The FL2VA download total was confirmed at 42.5 GiB before transfer. Ref2VA and BF16/full variants were not downloaded.

First test

Native local T2VA workflow, audio enabled, 124 frames at 24 fps (~5 seconds), 608x352 preview, 20 steps, fixed seed and simple prompt.

The prompt was accepted locally (node_errors: {}). The text encoder loaded 14,960 MB and the DiT loaded 19,996 MB. Sampling failed after 47.92 seconds at 0/20 steps. No MP4 was produced.

Error
NotImplementedError: The operator 'aten::_int_mm' is not currently implemented for the MPS device

The error occurs in the INT8 quantized comfy_kitchen path used by the DiT ConvRot implementation. PyTorch suggests PYTORCH_ENABLE_MPS_FALLBACK=1, but that would move the operation to CPU and would not constitute a satisfactory native MPS baseline.

Memory compression and swap were also non-zero after the failed run.

Recommendation

Please clarify whether Apple Silicon/MPS is expected to support the official INT8/NVFP4/AWQ ComfyUI workflow. A Diffusers/MPS route or an explicit BF16/CPU route may be worth testing separately. Until aten::_int_mm is implemented for MPS, the current quantized ComfyUI path should not be treated as a working Apple Silicon baseline.

主要语言
Python
星标
9.8k
派生
738
PR 合并指标
30 天内没有已合并 PR

环境准备

这个项目没有提供开发容器、Dockerfile 或贡献指南,环境需要你自己搭建:先看它的 README,通用步骤见我们的新手贡献指南。

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

MiniMax-AI/MiniMax-H3 的其他 Issue

查看 MiniMax-AI/MiniMax-H3 的全部 Issue

相似的 Issue

更多 Python Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。