kvcache-ai / kvcache-ai/ktransformers

请求增加对hunyuan image3.0 moe 80b a13b的支持

Open
#1,516 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
19.5k
Forks
1.6k
Avg merge
19h 32m
Merged PRs (30d)
27

Description

### 检查清单

- [x] 1. 如果您提出的不是新功能而是问题,请在讨论区发起讨论 https://github.com/kvcache-ai/ktransformers/discussions。否则该 issue 将被关闭
- [x] 2. 为方便社区交流,我将使用中文/英文或附上英文/中文翻译(如使用其他语言)。未附带翻译的非英文/中文内容可能会被关闭

### 需求背景

请问能够添加hunyuan3.0 image 80b a13b的支持吗?我在他们那里询问了,他们对这个有兴趣。希望能在16gb显存内的显卡利用KTransfomer跑上这个

### 相关资源

_No response_

Contributor guide

Open the contributing guide

Research direction

The issue names no files, tests, or entry points, and its related-resources section is empty. Clarify the required integration scope and acceptance criteria before implementation; the only stated completion target is running Hunyuan Image 3.0 MoE 80B A13B with KTransformers on a 16 GB GPU.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.