Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-27 21:46:57 +02:00
Code Issues Packages Projects Releases Wiki Activity
Files
b10877
llama.cpp/ggml
T
History
Piotr Wilkin (ilintar)Carl Philipp Klemmravel7524
 d4abd573f6 CUDA: size routed MoE MMQ N-tiles from typical expert width on RDNA3 (#28552) 
Recreated from #24546

---------

Co-authored-by: Carl Philipp Klemm <[email protected]>

* CUDA: pick MMQ tile size against ncols_opt set on the host side

Assisted-by: Claude Fable 5.1
Claude-Session: https://claude.ai/code/session_011SYPfRhKoUpU3gMsGxq6go

---------

Co-authored-by: ravel7524 <[email protected]>
Co-authored-by: Carl Philipp Klemm <[email protected]>
2026-09-09 13:25:54 +02:00
..
cmake
CUDA: replace GGML_FA_ALL_QUANTS with GGML_FA_QUANTS, more control over what is compiled (#28079)
2026-09-09 12:50:08 +02:00
include
ggml : update ggml_prec specification (#26675)
2026-09-08 09:06:24 +03:00
src
CUDA: size routed MoE MMQ N-tiles from typical expert width on RDNA3 (#28552)
2026-09-09 13:25:54 +02:00
.gitignore
vulkan : cmake integration (#8119)
2024-07-13 18:12:39 +02:00
CMakeLists.txt
CUDA: replace GGML_FA_ALL_QUANTS with GGML_FA_QUANTS, more control over what is compiled (#28079)
2026-09-09 12:50:08 +02:00