8000 Optimized DeepSeek V2/V3 implementation (MLA) by fairydreaming · Pull Request #11446 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

Optimized DeepSeek V2/V3 implementation (MLA) #11446

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 10 commits into from
Closed

Optimized DeepSeek V2/V3 implementation (MLA) #11446

Changes from 1 commit
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
93864cd
llama : experimental DeepSeek2 MLA implementation that caches latent …
sszymczy Jan 22, 2025
f0ce53f
Merge remote-tracking branch 'origin/master' into deepseek2-mla-exp
sszymczy Jan 24, 2025
de538aa
llama : optimize DeepSeek MLA implementation
sszymczy Jan 25, 2025
ce73063
llama : Update tensor names in DeepSeek2 MLA implementation.
sszymczy Jan 26, 2025
202f323
llama : add a second copy of c^KV cache in DeepSeek2 MLA to avoid tra…
sszymczy Jan 26, 2025
93c5937
llama : modified tensor permutations to multiply larger matrices duri…
sszymczy Jan 26, 2025
1eee98f
llama : removed unnecessary code in DeepSeek V2 implementation
sszymczy Jan 27, 2025
8ff0991
convert : make lint happy
sszymczy Jan 28, 2025
8a887de
llama : prompt processing optimizations in DeepSeek V2
sszymczy Jan 28, 2025
7654331
llama : avoid ggml_cont() is possible in DeepSeek V2 implementation
sszymczy Jan 30, 2025
8000
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Merge remote-tracking branch 'origin/master' into deepseek2-mla-exp
  • Loading branch information
@sszymczy
sszymczy committed Jan 24, 2025
commit f0ce53f158b12da1a61e8f55a8a954e8581bf9ad

This merge commit was added into this branch cleanly.

There are no new changes to show, but you can still view the diff.
0