wylab/llama.cpp
0
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-07 16:37:57 +02:00
Code Issues Packages Projects Releases Wiki Activity
10,809 Commits 778 Branches 7,351 Tags
v0.4.0
Commit Graph
1 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Laurent ZuijdwijkGitHubMarshall
 		ba8818cbf3 vulkan: handle larger batch sizes (>4) efficiently for IQ3_S mat-vec (#27449) 
* vulkan: handle larger batch sizes (>4) efficiently for IQ3_S mat-vec when NUM_COLS > 4. 5x perf at n=8

Assisted-by: Claude Opus 5

* adds 2 cases per quant type at `k=16*256` to the `all_types` mat-vec sweep

---------

Co-authored-by: Marshall <assistant@llama.cpp>
 2026-09-02 09:14:52 +03:00