【Hackathon 10th Spring No.50】【RFC】新增 MiniCPM4.1-8B 模型设计文档#1251
Open
cloudforge1 wants to merge 3 commits intoPaddlePaddle:masterfrom
Open
【Hackathon 10th Spring No.50】【RFC】新增 MiniCPM4.1-8B 模型设计文档#1251cloudforge1 wants to merge 3 commits intoPaddlePaddle:masterfrom
cloudforge1 wants to merge 3 commits intoPaddlePaddle:masterfrom
Conversation
Collaborator
5 tasks
Collaborator
直接在原来的RFC上修改即可,不需要新建一个文件。 |
Contributor
Author
|
好的,改为直接修改原 RFC 文件,稍后更新。 |
Per reviewer feedback (comment #4153770822), modify the original RFC file from PR PaddlePaddle#1183 directly rather than creating a separate file. - Delete: 20260708_add_minicpm41_8b_for_fastdeploy.md (new file) - Update: 20251114_add_minicpmV41_for_fastdeploy.md (existing file) - Content: H10 updated design with MLA reuse strategy
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 设计 FastDeploy 新增 MiniCPM4.1-8B 模型的推理支持方案。
核心策略
MLAAttentionBackend(源自 DeepSeek-v3),dense 层复用 Qwen3 模式主要内容
minicpm4.py(~400-500行)相关链接