mirrors/ollama-for-amd
1
0
Fork 0
mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-22 06:43:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

llm: Enable flash attention for mistral3 by default

Browse Source
This commit is contained in:
Jesse Gross
2025-12-04 12:16:52 -08:00
committed by Jesse Gross
parent 1108d8b34e
commit 9191dfaf05
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
fs/ggml/ggml.go
View File

@@ -831,6 +831,7 @@ func (f GGML) FlashAttention() bool {
return slices.Contains([]string{ return slices.Contains([]string{
"gemma3", "gemma3",
"gptoss", "gpt-oss", "gptoss", "gpt-oss",
"mistral3",
"qwen3", "qwen3moe", "qwen3", "qwen3moe",
"qwen3vl", "qwen3vlmoe", "qwen3vl", "qwen3vlmoe",
}, f.KV().String("general.architecture")) }, f.KV().String("general.architecture"))