diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-07-15 08:03:13 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-07-15 08:03:13 +0200 |
| commit | 2081b3fccb9923699bf4d5e926d8719fc1d12c39 (patch) | |
| tree | 61b3665214941b4857466fdea8220159d81a609e /convert_hf_to_gguf_update.py | |
| parent | 45fae1a14444622478774f9a417e1d417af1ca46 (diff) | |
Vulkan: a fresh start (#608)
* It compiles
* Seems to be working with coopmat
* Vulkan needs f32 precision for flash attention
* Vulkan: fix u_batch > 4096/n_active_experts
for coopmat1. Without this fix we get an assert.
We get the same assert in mainline too.
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'convert_hf_to_gguf_update.py')
0 files changed, 0 insertions, 0 deletions