highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-12-09 04:32:33 +01:00
Code Issues Packages Projects Releases Wiki Activity

Support Multiple LoRa Adapters (#7667)

Browse Source 
Closes #7627
This commit is contained in:
ItzCrazyKns
2024-11-28 00:30:04 +05:30
committed by GitHub
parent 940e62772e
commit e3936d4fb3
2 changed files with 26 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
llm/server.go
View File

@@ -144,10 +144,6 @@ func NewLlamaServer(gpus discover.GpuInfoList, model string, ggml *GGML, adapter
// Loop through potential servers
finalErr := errors.New("no suitable llama servers found")
if len(adapters) > 1 {
return nil, errors.New("ollama supports only one lora adapter, but multiple were provided")
}
rDir, err := runners.Refresh(build.EmbedFS)
if err != nil {
return nil, err
@@ -201,8 +197,9 @@ func NewLlamaServer(gpus discover.GpuInfoList, model string, ggml *GGML, adapter
}
if len(adapters) > 0 {
// TODO: applying multiple adapters is not supported by the llama.cpp server yet
params = append(params, "--lora", adapters[0])
for _, adapter := range adapters {
params = append(params, "--lora", adapter)
}
}
if len(projectors) > 0 {