mirrors/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-05-11 10:26:53 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

runner.go: Remove unused arguments

Browse source 
Now that server.cpp is gone, we don't need to keep passing arguments
that were only ignored and only kept for compatibility.
This commit is contained in:
Jesse Gross 2024-10-30 16:54:49 -07:00 • committed by Jesse Gross
parent 6cd566872b
commit a909417602
5 changed files with 1 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llm/server.go
View file

@ -186,7 +186,6 @@ func NewLlamaServer(gpus discover.GpuInfoList, model string, ggml *GGML, adapter
"--model", model,
"--ctx-size", strconv.Itoa(opts.NumCtx),
"--batch-size", strconv.Itoa(opts.NumBatch),
"--embedding",
}
if opts.NumGPU >= 0 {
@ -218,10 +217,6 @@ func NewLlamaServer(gpus discover.GpuInfoList, model string, ggml *GGML, adapter
params = append(params, "--threads", strconv.Itoa(defaultThreads))
}
if !opts.F16KV {
params = append(params, "--memory-f32")
}
flashAttnEnabled := envconfig.FlashAttention()
for _, g := range gpus {