Optimized DeepSeek V2/V3 implementation (MLA + flash attention)#12227
Closed
jukofyork wants to merge 5 commits intoggml-org:masterfrom
jukofyork:mla-with-flash-attention
Closed
Optimized DeepSeek V2/V3 implementation (MLA + flash attention)#12227jukofyork wants to merge 5 commits intoggml-org:masterfrom jukofyork:mla-with-flash-attention
jukofyork wants to merge 5 commits intoggml-org:masterfrom
jukofyork:mla-with-flash-attention
Commits
Commits on Mar 6, 2025
- committed
- committed
- committed
- committed
- committed
