mirrors/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-05-11 18:36:41 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #4218 from dhiltgen/auto_parallel

Browse source 
Enable concurrency by default
This commit is contained in:
Daniel Hiltgen 2024-07-01 08:32:29 -07:00 • committed by GitHub
commit 3518aaef33
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 175 additions and 73 deletions
Download patch file Download diff file Expand all files Collapse all files

13
llm/server.go
View file

@ -82,7 +82,7 @@ func LoadModel(model string, maxArraySize int) (*GGML, error) {
// NewLlamaServer will run a server for the given GPUs
// The gpu list must be a single family.
func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, projectors []string, opts api.Options) (LlamaServer, error) {
func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, projectors []string, opts api.Options, numParallel int) (LlamaServer, error) {
var err error
var cpuRunner string
var estimate MemoryEstimate
@ -218,8 +218,10 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
// Windows CUDA should not use mmap for best performance
// Linux with a model larger than free space, mmap leads to thrashing
// For CPU loads we want the memory to be allocated, not FS cache
if (runtime.GOOS == "windows" && gpus[0].Library == "cuda" && opts.UseMMap == api.TriStateUndefined) ||
(runtime.GOOS == "linux" && systemFreeMemory < estimate.TotalSize && opts.UseMMap == api.TriStateUndefined) ||
(gpus[0].Library == "cpu" && opts.UseMMap == api.TriStateUndefined) ||
opts.UseMMap == api.TriStateFalse {
params = append(params, "--no-mmap")
}
@ -232,15 +234,6 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
params = append(params, "--numa")
}
numParallel := envconfig.NumParallel
// TODO (jmorganca): multimodal models don't support parallel yet
// see https://github.com/ollama/ollama/issues/4165
if len(projectors) > 0 {
numParallel = 1
slog.Warn("multimodal models don't support parallel requests yet")
}
params = append(params, "--parallel", fmt.Sprintf("%d", numParallel))
if estimate.TensorSplit != "" {