Skip to content

GitLab

Unverified Commit 6a1b4713 authored by Daniel Hiltgen's avatar Daniel Hiltgen Committed by GitHub
Browse files

Merge pull request #4430 from dhiltgen/gpu_info 

Remove VRAM convergence check for windows
parents 7ca71a6b ec231a79
Show whitespace changes
Inline Side-by-side
Showing with 3 additions and 2 deletions
server/sched.go
View file @ 6a1b4713
...@@ -6,6 +6,7 @@ import ( ...@@ -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 ...@@ -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
} }
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment