root
/
ollama
mirror of https://github.com/ollama/ollama.git
1
0
Fork 0
Code Issues Actions Packages Projects Releases Wiki Activity

Merge 33e253a1bd into bc71278670

This commit is contained in:
frob 2025-10-07 13:55:05 +03:00 committed by GitHub
parent bc71278670 33e253a1bd
commit d5f1a09e16
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 14 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
api/types.go
View File

@ -398,6 +398,7 @@ type Runner struct {
MainGPU int `json:"main_gpu,omitempty"`
UseMMap *bool `json:"use_mmap,omitempty"`
NumThread int `json:"num_thread,omitempty"`
NumParallel int `json:"num_parallel,omitempty"`
}
// EmbedRequest is the request passed to [Client.Embed].
@ -836,6 +837,7 @@ func DefaultOptions() Options {
NumGPU: -1, // -1 here indicates that NumGPU should be set dynamically
NumThread: 0, // let the runtime decide
UseMMap: nil,
NumParallel: int(envconfig.NumParallel()),
},
}
}

2
server/sched.go
View File

@ -392,7 +392,7 @@ func (pending *LlmRequest) useLoadedRunner(runner *runnerRef, finished chan *Llm
// load creates a new model based on req and loads it. If requireFull is true then the model must be loaded fully onto GPUs
// (if any). Returns whether the scheduler needs to evict a model to make this one fit.
func (s *Scheduler) load(req *LlmRequest, f *ggml.GGML, gpus discover.GpuInfoList, requireFull bool) bool {
numParallel := max(int(envconfig.NumParallel()), 1)
numParallel := max(req.opts.NumParallel, 1)
// Embedding models should always be loaded with parallel=1
if req.model.CheckCapabilities(model.CapabilityCompletion) != nil {