mirror of
https://github.com/ollama/ollama.git
synced 2025-12-09 04:52:34 +01:00
runner.go: Remove unused arguments
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:
@@ -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 {
|
||||
|
||||
Reference in New Issue
Block a user