Skip to content

Navigation Menu

Explore
By company size
By use case
By industry
View all solutions
Topics
- AI
- DevOps
- Security
- Software Development
- View all
Explore
- GitHub Sponsors
  Fund open source developers
- The ReadME Project
  GitHub community articles
Repositories
- Enterprise platform
  AI-powered developer platform
Available add-ons
Pricing

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

ggml-org / llama.cpp Public

Notifications You must be signed in to change notification settings
Fork 11k
Star 76.3k

Code
Issues 356
Pull requests 402
Discussions
Actions
Projects 9
Wiki
Security
Insights

Additional navigation options

Code
Issues
Pull requests
Discussions
Actions
Projects
Wiki
Security
Insights

DeepSeek V2/V3 implementation refactored to allow non-MLA and MLA#12313

Closed

jukofyork wants to merge 11 commits intoggml-org:masterggml-org/llama.cpp:masterfrom jukofyork:mla-final-refactorjukofyork/llama.cpp:mla-final-refactorCopy head branch name to clipboard

Conversation Commits11 (11)Checks Files changed

Commits

Commits on Mar 10, 2025

Initial commit of all reformatted changes for deepseek2-mla
jukofyork
committed
Added missing MLA flags
jukofyork
committed
Added missing default to llama_context_default_params()
jukofyork
committed
Fixed typo in mla_attn name
jukofyork
committed
Fixed bad formatting of build_deepseek2()
jukofyork
committed
Switched to have first n_rot so can use context shifting later
jukofyork
committed
Changed comment as shifting *could* be implemented now
jukofyork
committed
Final tidy up and added TODOs and extra comments
jukofyork
committed
Removed unused local variables from llm_build_kv()
jukofyork
committed
Removed trailing whitespace in convert_hf_to_gguf.py
jukofyork
committed
Added optimised version of MQA for MLA to llm_build_kqv()
jukofyork
committed

Footer

© 2025 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Docs
Contact

You can’t perform that action at this time.