baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Merge pull request #809 from jmorganca/mxyng/fix-gpu

Browse source 
fix: regression unsupported metal types
This commit is contained in:
Michael Yang 2023-10-17 08:40:40 -07:00 committed by GitHub
commit c031c211d1
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
llm/llama.go
View file

@ -292,13 +292,10 @@ func newLlama(model string, adapters []string, runners []ModelRunner, numLayers
"--rope-freq-base", fmt.Sprintf("%f", opts.RopeFrequencyBase),
"--rope-freq-scale", fmt.Sprintf("%f", opts.RopeFrequencyScale),
"--batch-size", fmt.Sprintf("%d", opts.NumBatch),
"--n-gpu-layers", fmt.Sprintf("%d", numGPU),
"--embedding",
}
if numGPU > 0 {
params = append(params, "--n-gpu-layers", fmt.Sprintf("%d", numGPU))
}
if opts.NumGQA > 0 {
params = append(params, "--gqa", fmt.Sprintf("%d", opts.NumGQA))
}