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
10,841 Commits 778 Branches 7,351 Tags
0cc4m/vulkan-mul-mm-refactor
Commit Graph
2 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Nathan WilsonandGitHub c7bda030e7 vulkan: fix FA dequant path engagement (#28190) 
Skip the nb[3] check when ne[3] == 1, the shader never reads it for a
single stream. Cache views carry the full-buffer stride there, so the old
check reduced to n_kv == kv_size and the path only engaged with the
cache full.
 2026-09-03 10:40:34 +02:00
Nathanw1014andGitHub dc72703fc6 vulkan : dequant q8_0 KV once in coopmat1 (#25494) 
* vulkan : dequant q8_0 KV once in coopmat1

Assisted-by: Claude (Opus 4.8)

* vulkan : fall back instead of aborting when FA scratch exceeds maxStorageBufferRange

* vulkan : require KV-cache layout in FA dequant path

Assisted-by: Claude (Opus 4.8)

* vulkan : skip FA dequant path on coopmat2

Assisted-by: Claude (Opus 4.8)

* tests : add contiguously-allocated quant K/V FA tests

Assisted-by: Claude (Opus 4.8)

* vulkan : trim comments

* vulkan : tighten permutation checks for FA path

* vulkan : set prealloc_x_need_sync after the FA dispatch

* vulkan : exclude Intel Xe1 from FA dequant path
 2026-08-19 17:44:15 +02:00