blob: b54440cd3d5394e30156265ea03a40178c9d73a4 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
diff --git a/llm/llama.go b/llm/llama.go
index 0b460e9..b79e04a 100644
--- a/llm/llama.go
+++ b/llm/llama.go
@@ -299,10 +299,6 @@ func newLlama(model string, adapters []string, runners []ModelRunner, numLayers
params = append(params, "--n-gpu-layers", fmt.Sprintf("%d", numGPU))
}
- if opts.NumGQA > 0 {
- params = append(params, "--gqa", fmt.Sprintf("%d", opts.NumGQA))
- }
-
if len(adapters) > 0 {
// TODO: applying multiple adapters is not supported by the llama.cpp server yet
params = append(params, "--lora", adapters[0])
|