matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-10 15:57:04 +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

4
llm/memory_test.go
View File

@@ -8,14 +8,14 @@ import (
"testing"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/envconfig"
"github.com/ollama/ollama/gpu"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestEstimateGPULayers(t *testing.T) {
envconfig.Debug = true
t.Setenv("OLLAMA_DEBUG", "1")
modelName := "dummy"
f, err := os.CreateTemp(t.TempDir(), modelName)
require.NoError(t, err)

8
llm/server.go
View File

@@ -163,7 +163,7 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
} else {
servers = serversForGpu(gpus[0]) // All GPUs in the list are matching Library and Variant
}
demandLib := envconfig.LLMLibrary
demandLib := envconfig.LLMLibrary()
if demandLib != "" {
serverPath := availableServers[demandLib]
if serverPath == "" {
@@ -195,7 +195,7 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
params = append(params, "--n-gpu-layers", fmt.Sprintf("%d", opts.NumGPU))
}
if envconfig.Debug {
if envconfig.Debug() {
params = append(params, "--verbose")
}
@@ -221,7 +221,7 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
params = append(params, "--memory-f32")
}
flashAttnEnabled := envconfig.FlashAttention
flashAttnEnabled := envconfig.FlashAttention()
for _, g := range gpus {
// only cuda (compute capability 7+) and metal support flash attention
@@ -382,7 +382,7 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
}
slog.Info("starting llama server", "cmd", s.cmd.String())
if envconfig.Debug {
if envconfig.Debug() {
filteredEnv := []string{}
for _, ev := range s.cmd.Env {
if strings.HasPrefix(ev, "CUDA_") ||