mirrors/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-05-11 18:36:41 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

bool

Browse source
This commit is contained in:
Michael Yang 2024-07-03 17:22:13 -07:00
parent 66fe77f084
commit 55cd3ddcca
8 changed files with 82 additions and 83 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llm/server.go
View file

@ -221,7 +221,7 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
params = append(params, "--memory-f32")
}
flashAttnEnabled := envconfig.FlashAttention
flashAttnEnabled := envconfig.FlashAttention()
for _, g := range gpus {
// only cuda (compute capability 7+) and metal support flash attention