OSSForks/ollama
1
0
Fork 0
mirror of https://github.com/zebrajr/ollama.git synced 2025-12-06 00:19:51 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

qwen3vl: enable flash attention by default (#12862)

Browse Source
This commit is contained in:
Michael Yang 2025-10-30 10:51:37 -07:00 committed by GitHub
parent ed78e127d0
commit 75e75d9afe
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
fs/ggml/ggml.go
View File

@ -895,8 +895,8 @@ func (f GGML) FlashAttention() bool {
return slices.Contains([]string{ return slices.Contains([]string{
"gemma3", "gemma3",
"gptoss", "gpt-oss", "gptoss", "gpt-oss",
"qwen3", "qwen3", "qwen3moe",
"qwen3moe", "qwen3vl", "qwen3vlmoe",
}, f.KV().String("general.architecture")) }, f.KV().String("general.architecture"))
} }