highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-11-12 10:57:51 +01:00
Code Issues Packages Projects Releases Wiki Activity

llm: Enable flash attention by default for gemma3

Browse Source
This commit is contained in:
Jesse Gross
2025-10-15 10:22:03 -07:00
committed by Jesse Gross
parent 0d713051a2
commit c3c85aa06c
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

@@ -893,6 +893,7 @@ func (f GGML) SupportsFlashAttention() bool {
// FlashAttention checks if the model should enable flash attention // FlashAttention checks if the model should enable flash attention
func (f GGML) FlashAttention() bool { func (f GGML) FlashAttention() bool {
return slices.Contains([]string{ return slices.Contains([]string{
"gemma3",
"gptoss", "gpt-oss", "gptoss", "gpt-oss",
"qwen3", "qwen3",
"qwen3moe", "qwen3moe",