diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-07-05 15:14:12 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-07-05 15:14:12 +0200 |
| commit | 4622fadc2a2665b731a5887f93e295f0331ed80e (patch) | |
| tree | 31fef5de7e4282cef3fd9b6cd3505ddbfa104672 /ggml/src/ggml-quants.c | |
| parent | 0678427f82686e9bb37d02bf5842e451bb742808 (diff) | |
Vulkan: flash attention for DeepSeek models (#584)
* vulkan: support mixed/deepseekR1 FA head sizes (#14509)
* vulkan: better parameterize FA by head sizes
* vulkan: support mixed/deepseekR1 FA head sizes
* Fix the FA cherry-pick
---------
Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'ggml/src/ggml-quants.c')
0 files changed, 0 insertions, 0 deletions