【Hackathon 10th Spring No.47】MiniMax-M1 模型设计文档#1338
Open
bobby-cloudforge wants to merge 1 commit intoPaddlePaddle:masterfrom
Open
【Hackathon 10th Spring No.47】MiniMax-M1 模型设计文档#1338bobby-cloudforge wants to merge 1 commit intoPaddlePaddle:masterfrom
bobby-cloudforge wants to merge 1 commit intoPaddlePaddle:masterfrom
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
概述
本 RFC 为 FastDeploy 新增 MiniMax-M1 模型推理支持的设计文档。
核心挑战
MiniMax-M1 (456B MoE, 45.9B active) 采用 80 层混合架构(10 层标准 GQA + 70 层 Lightning Attention 线性注意力),需要:
@triton.jit内核从 vLLM 移植至 FastDeploy Triton 兼容层attn_type_list选择 GQA 或线性注意力方案选型
利用 FastDeploy 已有的
enable_compat_on_triton_kernel装饰器实现 Paddle 张量 ↔ Triton 指针的隐式转换,直接移植 Triton 内核,维护成本远低于 CUDA C++ 翻译路线。复用与新增
相关链接