baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Merge pull request #4430 from dhiltgen/gpu_info

Browse source 
Remove VRAM convergence check for windows
This commit is contained in:
Daniel Hiltgen 2024-05-14 10:59:06 -07:00 committed by GitHub
commit 6a1b471365
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 3 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
server/sched.go
View file

@ -6,6 +6,7 @@ import (
"fmt" "fmt"
"log/slog" "log/slog"
"reflect" "reflect"
"runtime"
"sort" "sort"
"strings" "strings"
"sync" "sync"
@ -487,8 +488,8 @@ func (runner *runnerRef) needsReload(ctx context.Context, req *LlmRequest) bool
func (runner *runnerRef) waitForVRAMRecovery() chan interface{} { func (runner *runnerRef) waitForVRAMRecovery() chan interface{} {
finished := make(chan interface{}, 1) finished := make(chan interface{}, 1)
// CPU or Metal don't need checking, so no waiting required // CPU or Metal don't need checking, so no waiting required, windows can page VRAM, and the APIs we query tend to be optimistic on free space
if len(runner.gpus) == 1 && (runner.gpus[0].Library == "cpu" || runner.gpus[0].Library == "metal") { if (len(runner.gpus) == 1 && (runner.gpus[0].Library == "cpu" || runner.gpus[0].Library == "metal")) || runtime.GOOS == "windows" {
finished <- struct{}{} finished <- struct{}{}
return finished return finished
} }