matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-11 08:17:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #5473 from ollama/mxyng/environ

Browse Source 
fix: environ lookup
This commit is contained in:
Michael Yang
2024-07-31 10:18:05 -07:00
committed by GitHub
parent 71399aa682 85d9d73a72
commit 5c1912769e
27 changed files with 547 additions and 515 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
server/sched_test.go
View File

@@ -12,7 +12,6 @@ import (
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/app/lifecycle"
"github.com/ollama/ollama/envconfig"
"github.com/ollama/ollama/format"
"github.com/ollama/ollama/gpu"
"github.com/ollama/ollama/llm"
@@ -272,7 +271,7 @@ func TestRequestsMultipleLoadedModels(t *testing.T) {
c.req.opts.NumGPU = 0 // CPU load, will be allowed
d := newScenarioRequest(t, ctx, "ollama-model-3c", 30, nil) // Needs prior unloaded
envconfig.MaxRunners = 1
t.Setenv("OLLAMA_MAX_LOADED_MODELS", "1")
s.newServerFn = a.newServer
slog.Info("a")
s.pendingReqCh <- a.req
@@ -291,7 +290,7 @@ func TestRequestsMultipleLoadedModels(t *testing.T) {
require.Len(t, s.loaded, 1)
s.loadedMu.Unlock()
envconfig.MaxRunners = 0
t.Setenv("OLLAMA_MAX_LOADED_MODELS", "0")
s.newServerFn = b.newServer
slog.Info("b")
s.pendingReqCh <- b.req
@@ -362,7 +361,7 @@ func TestGetRunner(t *testing.T) {
a := newScenarioRequest(t, ctx, "ollama-model-1a", 10, &api.Duration{Duration: 2 * time.Millisecond})
b := newScenarioRequest(t, ctx, "ollama-model-1b", 10, &api.Duration{Duration: 2 * time.Millisecond})
c := newScenarioRequest(t, ctx, "ollama-model-1c", 10, &api.Duration{Duration: 2 * time.Millisecond})
envconfig.MaxQueuedRequests = 1
t.Setenv("OLLAMA_MAX_QUEUE", "1")
s := InitScheduler(ctx)
s.getGpuFn = getGpuFn
s.getCpuFn = getCpuFn