matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-10 07:46:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

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