feat: support Kimi K3 - #1410
Open
sufubao wants to merge 1 commit into
Open
Conversation
Contributor
|
Caution The consumer version of Gemini Code Assist on GitHub has been sunset. All code review activity has officially ceased. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
新增 Kimi K3 文本模型支持：复用 Kimi Linear/KDA 路径，实现 block AttnRes、latent MoE、SiTU 激活、MXFP4 expert 权重和嵌套
text_config权重加载；同时增加可选 MoonEP backend 与 Kimi K3 XTML tool-call parser。分支从最新
upstream/main提取为单个提交，未包含原开发分支中的启动、压测脚本和 Hopper all-reduce 调优。验证：K3/MXFP4/MoonEP/tool-call 单测与 CUDA 数值测试 45/45 通过，Kimi linear cache 测试 7/7 通过；2-layer K3、TP8 的
/v1/chat/completionssmoke 通过（隔离现有 TP16 服务，使用--disable_cudagraph --disable_symm_mem_allreduce --disable_flashinfer_allreduce）。Black、compileall 和git diff --check通过。