Browse Source

lint

mxyng/fix-memory
Michael Yang 2 years ago
parent
commit
b732beba6a
  1. 1
      .gitattributes
  2. 2
      .github/workflows/test.yaml
  3. 18
      .golangci.yaml
  4. 3
      api/client.go
  5. 4
      api/types_test.go
  6. 4
      app/lifecycle/getstarted_nonwindows.go
  7. 1
      app/lifecycle/getstarted_windows.go
  8. 2
      app/lifecycle/logging.go
  9. 2
      app/lifecycle/logging_nonwindows.go
  10. 4
      app/lifecycle/logging_test.go
  11. 2
      app/lifecycle/server.go
  12. 3
      app/lifecycle/updater.go
  13. 4
      app/lifecycle/updater_nonwindows.go
  14. 5
      app/lifecycle/updater_windows.go
  15. 4
      app/tray/tray_nonwindows.go
  16. 4
      app/tray/wintray/eventloop.go
  17. 5
      app/tray/wintray/tray.go
  18. 3
      auth/auth.go
  19. 2
      cmd/cmd.go
  20. 2
      cmd/interactive.go
  21. 4
      cmd/start_darwin.go
  22. 4
      cmd/start_default.go
  23. 2
      cmd/start_windows.go
  24. 3
      convert/convert_llama.go
  25. 6
      convert/convert_test.go
  26. 4
      convert/fs.go
  27. 5
      convert/reader_safetensors.go
  28. 3
      format/format.go
  29. 4
      gpu/amd_common.go
  30. 9
      gpu/amd_hip_windows.go
  31. 2
      gpu/amd_linux.go
  32. 6
      gpu/amd_windows.go
  33. 4
      gpu/assets.go
  34. 19
      gpu/gpu.go
  35. 1
      gpu/gpu_darwin.go
  36. 2
      gpu/gpu_info.h
  37. 10
      gpu/gpu_linux.go
  38. 10
      gpu/gpu_windows.go
  39. 6
      integration/utils_test.go
  40. 5
      llm/llm.go
  41. 5
      llm/memory_test.go
  42. 14
      llm/server.go
  43. 3
      main.go
  44. 20
      openai/openai.go
  45. 11
      openai/openai_test.go
  46. 12
      parser/parser_test.go
  47. 3
      progress/bar.go
  48. 4
      readline/buffer.go
  49. 4
      readline/errors.go
  50. 6
      readline/term_linux.go
  51. 6
      server/download.go
  52. 6
      server/images.go
  53. 4
      server/manifest.go
  54. 2
      server/manifest_test.go
  55. 1
      server/model_test.go
  56. 1
      server/prompt_test.go
  57. 14
      server/routes.go
  58. 7
      server/routes_create_test.go
  59. 1
      server/routes_delete_test.go
  60. 1
      server/routes_list_test.go
  61. 1
      server/routes_test.go
  62. 2
      server/sched.go
  63. 18
      server/sched_test.go
  64. 6
      server/upload.go
  65. 3
      template/template.go
  66. 1
      template/template_test.go
  67. 6
      types/errtypes/errtypes.go
  68. 2
      types/model/name.go

1
.gitattributes

@ -1 +1,2 @@
llm/ext_server/* linguist-vendored
* text eol=lf

2
.github/workflows/test.yaml

@ -273,7 +273,7 @@ jobs:
if: ${{ startsWith(matrix.os, 'macos-') }}
- uses: golangci/golangci-lint-action@v6
with:
args: --timeout 8m0s -v ${{ startsWith(matrix.os, 'windows-') && '' || '--disable gofmt --disable goimports' }}
args: --timeout 8m0s -v
test:
strategy:
matrix:

18
.golangci.yaml

@ -7,22 +7,32 @@ linters:
- bodyclose
- containedctx
- contextcheck
- errcheck
- exportloopref
- gci
- gocheckcompilerdirectives
# conditionally enable this on linux/macos
# - gofmt
# - goimports
- gofmt
- gofumpt
- gosimple
- govet
- ineffassign
- intrange
- makezero
- misspell
- nilerr
- nolintlint
- nosprintfhostport
- staticcheck
- tenv
- testifylint
- unconvert
- unused
- usestdlibvars
- wastedassign
- whitespace
- usestdlibvars
linters-settings:
gci:
sections: [standard, default, localmodule]
severity:
default-severity: error
rules:

3
api/client.go

@ -18,6 +18,7 @@ import (
"bytes"
"context"
"encoding/json"
"errors"
"fmt"
"io"
"net/http"
@ -172,7 +173,7 @@ func (c *Client) stream(ctx context.Context, method, path string, data any, fn f
}
if errorResponse.Error != "" {
return fmt.Errorf(errorResponse.Error)
return errors.New(errorResponse.Error)
}
if response.StatusCode >= http.StatusBadRequest {

4
api/types_test.go

@ -2,7 +2,7 @@ package api
import (
"encoding/json"
"fmt"
"errors"
"math"
"testing"
"time"
@ -192,7 +192,7 @@ func TestUseMmapFormatParams(t *testing.T) {
"use_mmap": {"foo"},
},
exp: nil,
err: fmt.Errorf("invalid bool value [foo]"),
err: errors.New("invalid bool value [foo]"),
},
}

4
app/lifecycle/getstarted_nonwindows.go

@ -2,8 +2,8 @@
package lifecycle
import "fmt"
import "errors"
func GetStarted() error {
return fmt.Errorf("GetStarted not implemented")
return errors.New("not implemented")
}

1
app/lifecycle/getstarted_windows.go

@ -34,7 +34,6 @@ func GetStarted() error {
Sys: &syscall.SysProcAttr{CreationFlags: CREATE_NEW_CONSOLE, HideWindow: false},
}
proc, err := os.StartProcess(args[0], args, attrs)
if err != nil {
return fmt.Errorf("unable to start getting started shell %w", err)
}

2
app/lifecycle/logging.go

@ -27,7 +27,7 @@ func InitLogging() {
// TODO - write one-line to the app.log file saying we're running in console mode to help avoid confusion
} else {
rotateLogs(AppLogFile)
logFile, err = os.OpenFile(AppLogFile, os.O_APPEND|os.O_WRONLY|os.O_CREATE, 0755)
logFile, err = os.OpenFile(AppLogFile, os.O_APPEND|os.O_WRONLY|os.O_CREATE, 0o755)
if err != nil {
slog.Error(fmt.Sprintf("failed to create server log %v", err))
return

2
app/lifecycle/logging_nonwindows.go

@ -5,5 +5,5 @@ package lifecycle
import "log/slog"
func ShowLogs() {
slog.Warn("ShowLogs not yet implemented")
slog.Warn("not implemented")
}

4
app/lifecycle/logging_test.go

@ -17,7 +17,7 @@ func TestRotateLogs(t *testing.T) {
// No log exists
rotateLogs(logFile)
require.NoError(t, os.WriteFile(logFile, []byte("1"), 0644))
require.NoError(t, os.WriteFile(logFile, []byte("1"), 0o644))
assert.FileExists(t, logFile)
// First rotation
rotateLogs(logFile)
@ -32,7 +32,7 @@ func TestRotateLogs(t *testing.T) {
assert.NoFileExists(t, logFile)
for i := 2; i <= LogRotationCount+1; i++ {
require.NoError(t, os.WriteFile(logFile, []byte(strconv.Itoa(i)), 0644))
require.NoError(t, os.WriteFile(logFile, []byte(strconv.Itoa(i)), 0o644))
assert.FileExists(t, logFile)
rotateLogs(logFile)
assert.NoFileExists(t, logFile)

2
app/lifecycle/server.go

@ -55,7 +55,7 @@ func start(ctx context.Context, command string) (*exec.Cmd, error) {
}
rotateLogs(ServerLogFile)
logFile, err := os.OpenFile(ServerLogFile, os.O_APPEND|os.O_WRONLY|os.O_CREATE, 0755)
logFile, err := os.OpenFile(ServerLogFile, os.O_APPEND|os.O_WRONLY|os.O_CREATE, 0o755)
if err != nil {
return nil, fmt.Errorf("failed to create server log: %w", err)
}

3
app/lifecycle/updater.go

@ -15,6 +15,7 @@ import (
"path"
"path/filepath"
"runtime"
"strconv"
"strings"
"time"
@ -46,7 +47,7 @@ func IsNewReleaseAvailable(ctx context.Context) (bool, UpdateResponse) {
query.Add("os", runtime.GOOS)
query.Add("arch", runtime.GOARCH)
query.Add("version", version.Version)
query.Add("ts", fmt.Sprintf("%d", time.Now().Unix()))
query.Add("ts", strconv.FormatInt(time.Now().Unix(), 10))
nonce, err := auth.NewNonce(rand.Reader, 16)
if err != nil {

4
app/lifecycle/updater_nonwindows.go

@ -4,9 +4,9 @@ package lifecycle
import (
"context"
"fmt"
"errors"
)
func DoUpgrade(cancel context.CancelFunc, done chan int) error {
return fmt.Errorf("DoUpgrade not yet implemented")
return errors.New("not implemented")
}

5
app/lifecycle/updater_windows.go

@ -2,6 +2,7 @@ package lifecycle
import (
"context"
"errors"
"fmt"
"log/slog"
"os"
@ -15,7 +16,7 @@ func DoUpgrade(cancel context.CancelFunc, done chan int) error {
return fmt.Errorf("failed to lookup downloads: %s", err)
}
if len(files) == 0 {
return fmt.Errorf("no update downloads found")
return errors.New("no update downloads found")
} else if len(files) > 1 {
// Shouldn't happen
slog.Warn(fmt.Sprintf("multiple downloads found, using first one %v", files))
@ -64,7 +65,7 @@ func DoUpgrade(cancel context.CancelFunc, done chan int) error {
}
} else {
// TODO - some details about why it didn't start, or is this a pedantic error case?
return fmt.Errorf("installer process did not start")
return errors.New("installer process did not start")
}
// TODO should we linger for a moment and check to make sure it's actually running by checking the pid?

4
app/tray/tray_nonwindows.go

@ -3,11 +3,11 @@
package tray
import (
"fmt"
"errors"
"github.com/ollama/ollama/app/tray/commontray"
)
func InitPlatformTray(icon, updateIcon []byte) (commontray.OllamaTray, error) {
return nil, fmt.Errorf("NOT IMPLEMENTED YET")
return nil, errors.New("not implemented")
}

4
app/tray/wintray/eventloop.go

@ -11,9 +11,7 @@ import (
"golang.org/x/sys/windows"
)
var (
quitOnce sync.Once
)
var quitOnce sync.Once
func (t *winTray) Run() {
nativeLoop()

5
app/tray/wintray/tray.go

@ -13,8 +13,9 @@ import (
"sync"
"unsafe"
"github.com/ollama/ollama/app/tray/commontray"
"golang.org/x/sys/windows"
"github.com/ollama/ollama/app/tray/commontray"
)
// Helpful sources: https://github.com/golang/exp/blob/master/shiny/driver/internal/win32
@ -414,7 +415,7 @@ func iconBytesToFilePath(iconBytes []byte) (string, error) {
iconFilePath := filepath.Join(os.TempDir(), "ollama_temp_icon_"+dataHash)
if _, err := os.Stat(iconFilePath); os.IsNotExist(err) {
if err := os.WriteFile(iconFilePath, iconBytes, 0644); err != nil {
if err := os.WriteFile(iconFilePath, iconBytes, 0o644); err != nil {
return "", err
}
}

3
auth/auth.go

@ -5,6 +5,7 @@ import (
"context"
"crypto/rand"
"encoding/base64"
"errors"
"fmt"
"io"
"log/slog"
@ -78,7 +79,7 @@ func Sign(ctx context.Context, bts []byte) (string, error) {
publicKey := ssh.MarshalAuthorizedKey(privateKey.PublicKey())
parts := bytes.Split(publicKey, []byte(" "))
if len(parts) < 2 {
return "", fmt.Errorf("malformed public key")
return "", errors.New("malformed public key")
}
signedData, err := privateKey.Sign(rand.Reader, bts)

2
cmd/cmd.go

@ -1160,7 +1160,7 @@ func checkServerHeartbeat(cmd *cobra.Command, _ []string) error {
return err
}
if err := startApp(cmd.Context(), client); err != nil {
return fmt.Errorf("could not connect to ollama app, is it running?")
return errors.New("could not connect to ollama app, is it running?")
}
}
return nil

2
cmd/interactive.go

@ -604,7 +604,7 @@ func getImageData(filePath string) ([]byte, error) {
// Check if the file size exceeds 100MB
var maxSize int64 = 100 * 1024 * 1024 // 100MB in bytes
if info.Size() > maxSize {
return nil, fmt.Errorf("file size exceeds maximum limit (100MB)")
return nil, errors.New("file size exceeds maximum limit (100MB)")
}
buf = make([]byte, info.Size())

4
cmd/start_darwin.go

@ -2,7 +2,7 @@ package cmd
import (
"context"
"fmt"
"errors"
"os"
"os/exec"
"strings"
@ -20,7 +20,7 @@ func startApp(ctx context.Context, client *api.Client) error {
return err
}
if !strings.Contains(link, "Ollama.app") {
return fmt.Errorf("could not find ollama app")
return errors.New("could not find ollama app")
}
path := strings.Split(link, "Ollama.app")
if err := exec.Command("/usr/bin/open", "-a", path[0]+"Ollama.app").Run(); err != nil {

4
cmd/start_default.go

@ -4,11 +4,11 @@ package cmd
import (
"context"
"fmt"
"errors"
"github.com/ollama/ollama/api"
)
func startApp(ctx context.Context, client *api.Client) error {
return fmt.Errorf("could not connect to ollama server, run 'ollama serve' to start it")
return errors.New("could not connect to ollama server, run 'ollama serve' to start it")
}

2
cmd/start_windows.go

@ -31,7 +31,7 @@ func startApp(ctx context.Context, client *api.Client) error {
// Finally look in the path
appExe, err = exec.LookPath(AppName)
if err != nil {
return fmt.Errorf("could not locate ollama app")
return errors.New("could not locate ollama app")
}
}
}

3
convert/convert_llama.go

@ -5,9 +5,10 @@ import (
"fmt"
"strings"
"github.com/ollama/ollama/llm"
"github.com/pdevine/tensor"
"github.com/pdevine/tensor/native"
"github.com/ollama/ollama/llm"
)
type llama struct {

6
convert/convert_test.go

@ -2,6 +2,7 @@ package convert
import (
"crypto/sha256"
"encoding/hex"
"encoding/json"
"flag"
"fmt"
@ -14,8 +15,9 @@ import (
"slices"
"testing"
"github.com/ollama/ollama/llm"
"golang.org/x/exp/maps"
"github.com/ollama/ollama/llm"
)
func convertFull(t *testing.T, fsys fs.FS) (*os.File, llm.KV, llm.Tensors) {
@ -99,7 +101,7 @@ func TestConvertFull(t *testing.T) {
t.Fatal(err)
}
actual[tensor.Name] = fmt.Sprintf("%x", sha256sum.Sum(nil))
actual[tensor.Name] = hex.EncodeToString(sha256sum.Sum(nil))
}
expectFile, err := os.Open(filepath.Join("testdata", fmt.Sprintf("%s.json", tt)))

4
convert/fs.go

@ -10,8 +10,8 @@ import (
)
type ZipReader struct {
r *zip.Reader
p string
r *zip.Reader
p string
// limit is the maximum size of a file that can be read directly
// from the zip archive. Files larger than this size will be extracted

5
convert/reader_safetensors.go

@ -111,8 +111,9 @@ func (st safetensor) WriteTo(w io.Writer) (int64, error) {
return 0, err
}
for _, b := range u16s {
f32s = append(f32s, float16.Frombits(b).Float32())
f32s = make([]float32, len(u16s))
for i := range u16s {
f32s[i] = float16.Frombits(u16s[i]).Float32()
}
case "BF16":

3
format/format.go

@ -3,6 +3,7 @@ package format
import (
"fmt"
"math"
"strconv"
)
const (
@ -28,6 +29,6 @@ func HumanNumber(b uint64) string {
case b >= Thousand:
return fmt.Sprintf("%.0fK", float64(b)/Thousand)
default:
return fmt.Sprintf("%d", b)
return strconv.FormatUint(b, 10)
}
}

4
gpu/amd_common.go

@ -3,7 +3,7 @@
package gpu
import (
"fmt"
"errors"
"log/slog"
"os"
"path/filepath"
@ -95,5 +95,5 @@ func commonAMDValidateLibDir() (string, error) {
}
}
return "", fmt.Errorf("no suitable rocm found, falling back to CPU")
return "", errors.New("no suitable rocm found, falling back to CPU")
}

9
gpu/amd_hip_windows.go

@ -1,6 +1,7 @@
package gpu
import (
"errors"
"fmt"
"log/slog"
"syscall"
@ -76,7 +77,7 @@ func (hl *HipLib) Release() {
func (hl *HipLib) AMDDriverVersion() (driverMajor, driverMinor int, err error) {
if hl.dll == 0 {
return 0, 0, fmt.Errorf("dll has been unloaded")
return 0, 0, errors.New("dll has been unloaded")
}
var version int
status, _, err := syscall.SyscallN(hl.hipDriverGetVersion, uintptr(unsafe.Pointer(&version)))
@ -110,7 +111,7 @@ func (hl *HipLib) HipGetDeviceCount() int {
func (hl *HipLib) HipSetDevice(device int) error {
if hl.dll == 0 {
return fmt.Errorf("dll has been unloaded")
return errors.New("dll has been unloaded")
}
status, _, err := syscall.SyscallN(hl.hipSetDevice, uintptr(device))
if status != hipSuccess {
@ -121,7 +122,7 @@ func (hl *HipLib) HipSetDevice(device int) error {
func (hl *HipLib) HipGetDeviceProperties(device int) (*hipDevicePropMinimal, error) {
if hl.dll == 0 {
return nil, fmt.Errorf("dll has been unloaded")
return nil, errors.New("dll has been unloaded")
}
var props hipDevicePropMinimal
status, _, err := syscall.SyscallN(hl.hipGetDeviceProperties, uintptr(unsafe.Pointer(&props)), uintptr(device))
@ -134,7 +135,7 @@ func (hl *HipLib) HipGetDeviceProperties(device int) (*hipDevicePropMinimal, err
// free, total, err
func (hl *HipLib) HipMemGetInfo() (uint64, uint64, error) {
if hl.dll == 0 {
return 0, 0, fmt.Errorf("dll has been unloaded")
return 0, 0, errors.New("dll has been unloaded")
}
var totalMemory uint64
var freeMemory uint64

2
gpu/amd_linux.go

@ -393,7 +393,7 @@ func AMDValidateLibDir() (string, error) {
// If we still haven't found a usable rocm, the user will have to install it on their own
slog.Warn("amdgpu detected, but no compatible rocm library found. Either install rocm v6, or follow manual install instructions at https://github.com/ollama/ollama/blob/main/docs/linux.md#manual-install")
return "", fmt.Errorf("no suitable rocm found, falling back to CPU")
return "", errors.New("no suitable rocm found, falling back to CPU")
}
func AMDDriverVersion() (driverMajor, driverMinor int, err error) {

6
gpu/amd_windows.go

@ -2,7 +2,7 @@ package gpu
import (
"bytes"
"fmt"
"errors"
"log/slog"
"os"
"path/filepath"
@ -85,7 +85,7 @@ func AMDGetGPUInfo() []RocmGPUInfo {
n = bytes.IndexByte(props.GcnArchName[:], 0)
gfx := string(props.GcnArchName[:n])
slog.Debug("hip device", "id", i, "name", name, "gfx", gfx)
//slog.Info(fmt.Sprintf("[%d] Integrated: %d", i, props.iGPU)) // DOESN'T REPORT CORRECTLY! Always 0
// slog.Info(fmt.Sprintf("[%d] Integrated: %d", i, props.iGPU)) // DOESN'T REPORT CORRECTLY! Always 0
// TODO Why isn't props.iGPU accurate!?
if strings.EqualFold(name, iGPUName) {
slog.Info("unsupported Radeon iGPU detected skipping", "id", i, "name", name, "gfx", gfx)
@ -161,7 +161,7 @@ func AMDValidateLibDir() (string, error) {
// Should not happen on windows since we include it in the installer, but stand-alone binary might hit this
slog.Warn("amdgpu detected, but no compatible rocm library found. Please install ROCm")
return "", fmt.Errorf("no suitable rocm found, falling back to CPU")
return "", errors.New("no suitable rocm found, falling back to CPU")
}
func (gpus RocmGPUInfoList) RefreshFreeMemory() error {

4
gpu/assets.go

@ -42,7 +42,7 @@ func PayloadsDir() (string, error) {
return "", fmt.Errorf("failed to generate tmp dir: %w", err)
}
} else {
err = os.MkdirAll(tmpDir, 0755)
err = os.MkdirAll(tmpDir, 0o755)
if err != nil {
return "", fmt.Errorf("failed to generate tmp dir %s: %w", tmpDir, err)
}
@ -54,7 +54,7 @@ func PayloadsDir() (string, error) {
if err != nil {
return "", err
}
if _, err := pidFile.Write([]byte(fmt.Sprint(os.Getpid()))); err != nil {
if _, err := pidFile.Write([]byte(strconv.Itoa(os.Getpid()))); err != nil {
return "", err
}

19
gpu/gpu.go

@ -7,9 +7,9 @@ package gpu
#cgo windows LDFLAGS: -lpthread
#include "gpu_info.h"
*/
import "C"
import (
"fmt"
"log/slog"
@ -70,7 +70,6 @@ var CudaTegra string = os.Getenv("JETSON_JETPACK")
// Note: gpuMutex must already be held
func initCudaHandles() *cudaHandles {
// TODO - if the ollama build is CPU only, don't do these checks as they're irrelevant and confusing
cHandles := &cudaHandles{}
@ -211,14 +210,16 @@ func GetGPUInfo() GpuInfoList {
if err != nil {
slog.Warn("error looking up system memory", "error", err)
}
cpus = []CPUInfo{CPUInfo{
GpuInfo: GpuInfo{
memInfo: mem,
Library: "cpu",
Variant: cpuCapability,
ID: "0",
cpus = []CPUInfo{
{
GpuInfo: GpuInfo{
memInfo: mem,
Library: "cpu",
Variant: cpuCapability,
ID: "0",
},
},
}}
}
// Fallback to CPU mode if we're lacking required vector extensions on x86
if cpuCapability < GPURunnerCPUCapability && runtime.GOARCH == "amd64" {

1
gpu/gpu_darwin.go

@ -8,6 +8,7 @@ package gpu
#include "gpu_info_darwin.h"
*/
import "C"
import (
"runtime"

2
gpu/gpu_info.h

@ -67,4 +67,4 @@ void cpu_check_ram(mem_info_t *resp);
#include "gpu_info_oneapi.h"
#endif // __GPU_INFO_H__
#endif // __APPLE__
#endif // __APPLE__

10
gpu/gpu_linux.go

@ -43,10 +43,12 @@ var OneapiGlobs = []string{
"/usr/lib*/libze_intel_gpu.so*",
}
var CudartMgmtName = "libcudart.so*"
var NvcudaMgmtName = "libcuda.so*"
var NvmlMgmtName = "" // not currently wired on linux
var OneapiMgmtName = "libze_intel_gpu.so"
var (
CudartMgmtName = "libcudart.so*"
NvcudaMgmtName = "libcuda.so*"
NvmlMgmtName = "" // not currently wired on linux
OneapiMgmtName = "libze_intel_gpu.so"
)
func GetCPUMem() (memInfo, error) {
var mem memInfo

10
gpu/gpu_windows.go

@ -40,10 +40,12 @@ var OneapiGlobs = []string{
"c:\\Windows\\System32\\DriverStore\\FileRepository\\*\\ze_intel_gpu64.dll",
}
var CudartMgmtName = "cudart64_*.dll"
var NvcudaMgmtName = "nvcuda.dll"
var NvmlMgmtName = "nvml.dll"
var OneapiMgmtName = "ze_intel_gpu64.dll"
var (
CudartMgmtName = "cudart64_*.dll"
NvcudaMgmtName = "nvcuda.dll"
NvmlMgmtName = "nvml.dll"
OneapiMgmtName = "ze_intel_gpu64.dll"
)
func GetCPUMem() (memInfo, error) {
memStatus := MEMORYSTATUSEX{length: sizeofMemoryStatusEx}

6
integration/utils_test.go

@ -162,7 +162,7 @@ func PullIfMissing(ctx context.Context, client *api.Client, modelName string) er
fn := func(resp api.ProgressResponse) error {
// fmt.Print(".")
if !stallTimer.Reset(stallDuration) {
return fmt.Errorf("stall was detected, aborting status reporting")
return errors.New("stall was detected, aborting status reporting")
}
return nil
}
@ -180,7 +180,7 @@ func PullIfMissing(ctx context.Context, client *api.Client, modelName string) er
select {
case <-stallTimer.C:
return fmt.Errorf("download stalled")
return errors.New("download stalled")
case <-done:
return pullError
}
@ -243,7 +243,7 @@ func DoGenerate(ctx context.Context, t *testing.T, client *api.Client, genReq ap
// fmt.Print(".")
buf.Write([]byte(response.Response))
if !stallTimer.Reset(streamTimeout) {
return fmt.Errorf("stall was detected while streaming response, aborting")
return errors.New("stall was detected while streaming response, aborting")
}
return nil
}

5
llm/llm.go

@ -11,8 +11,9 @@ package llm
// #include <stdlib.h>
// #include "llama.h"
import "C"
import (
"fmt"
"errors"
"unsafe"
)
@ -33,7 +34,7 @@ func Quantize(infile, outfile string, ftype fileType) error {
params.ftype = ftype.Value()
if rc := C.llama_model_quantize(cinfile, coutfile, &params); rc != 0 {
return fmt.Errorf("failed to quantize model. This model architecture may not be supported, or you may need to upgrade Ollama to the latest version")
return errors.New("failed to quantize model. This model architecture may not be supported, or you may need to upgrade Ollama to the latest version")
}
return nil

5
llm/memory_test.go

@ -6,10 +6,11 @@ import (
"os"
"testing"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/gpu"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/gpu"
)
func TestEstimateGPULayers(t *testing.T) {

14
llm/server.go

@ -184,15 +184,15 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
params := []string{
"--model", model,
"--ctx-size", fmt.Sprintf("%d", opts.NumCtx),
"--batch-size", fmt.Sprintf("%d", opts.NumBatch),
"--ctx-size", strconv.Itoa(opts.NumCtx),
"--batch-size", strconv.Itoa(opts.NumBatch),
"--embedding",
}
params = append(params, "--log-disable")
if opts.NumGPU >= 0 {
params = append(params, "--n-gpu-layers", fmt.Sprintf("%d", opts.NumGPU))
params = append(params, "--n-gpu-layers", strconv.Itoa(opts.NumGPU))
}
if envconfig.Debug() {
@ -200,7 +200,7 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
}
if opts.MainGPU > 0 {
params = append(params, "--main-gpu", fmt.Sprintf("%d", opts.MainGPU))
params = append(params, "--main-gpu", strconv.Itoa(opts.MainGPU))
}
if len(adapters) > 0 {
@ -214,7 +214,7 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
}
if opts.NumThread > 0 {
params = append(params, "--threads", fmt.Sprintf("%d", opts.NumThread))
params = append(params, "--threads", strconv.Itoa(opts.NumThread))
}
if !opts.F16KV {
@ -260,7 +260,7 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
params = append(params, "--numa")
}
params = append(params, "--parallel", fmt.Sprintf("%d", numParallel))
params = append(params, "--parallel", strconv.Itoa(numParallel))
if estimate.TensorSplit != "" {
params = append(params, "--tensor-split", estimate.TensorSplit)
@ -425,7 +425,7 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
if strings.Contains(s.status.LastErrMsg, "unknown model") {
s.status.LastErrMsg = "this model is not supported by your version of Ollama. You may need to upgrade"
}
s.done <- fmt.Errorf(s.status.LastErrMsg)
s.done <- errors.New(s.status.LastErrMsg)
} else {
s.done <- err
}

3
main.go

@ -3,8 +3,9 @@ package main
import (
"context"
"github.com/ollama/ollama/cmd"
"github.com/spf13/cobra"
"github.com/ollama/ollama/cmd"
)
func main() {

20
openai/openai.go

@ -5,6 +5,7 @@ import (
"bytes"
"encoding/base64"
"encoding/json"
"errors"
"fmt"
"io"
"log/slog"
@ -14,6 +15,7 @@ import (
"time"
"github.com/gin-gonic/gin"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/types/model"
)
@ -367,24 +369,24 @@ func fromChatRequest(r ChatCompletionRequest) (*api.ChatRequest, error) {
for _, c := range content {
data, ok := c.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid message format")
return nil, errors.New("invalid message format")
}
switch data["type"] {
case "text":
text, ok := data["text"].(string)
if !ok {
return nil, fmt.Errorf("invalid message format")
return nil, errors.New("invalid message format")
}
messages = append(messages, api.Message{Role: msg.Role, Content: text})
case "image_url":
var url string
if urlMap, ok := data["image_url"].(map[string]any); ok {
if url, ok = urlMap["url"].(string); !ok {
return nil, fmt.Errorf("invalid message format")
return nil, errors.New("invalid message format")
}
} else {
if url, ok = data["image_url"].(string); !ok {
return nil, fmt.Errorf("invalid message format")
return nil, errors.New("invalid message format")
}
}
@ -400,17 +402,17 @@ func fromChatRequest(r ChatCompletionRequest) (*api.ChatRequest, error) {
}
if !valid {
return nil, fmt.Errorf("invalid image input")
return nil, errors.New("invalid image input")
}
img, err := base64.StdEncoding.DecodeString(url)
if err != nil {
return nil, fmt.Errorf("invalid message format")
return nil, errors.New("invalid message format")
}
messages = append(messages, api.Message{Role: msg.Role, Images: []api.ImageData{img}})
default:
return nil, fmt.Errorf("invalid message format")
return nil, errors.New("invalid message format")
}
}
default:
@ -423,7 +425,7 @@ func fromChatRequest(r ChatCompletionRequest) (*api.ChatRequest, error) {
toolCalls[i].Function.Name = tc.Function.Name
err := json.Unmarshal([]byte(tc.Function.Arguments), &toolCalls[i].Function.Arguments)
if err != nil {
return nil, fmt.Errorf("invalid tool call arguments")
return nil, errors.New("invalid tool call arguments")
}
}
messages = append(messages, api.Message{Role: msg.Role, ToolCalls: toolCalls})
@ -737,14 +739,12 @@ func (w *RetrieveWriter) Write(data []byte) (int, error) {
func (w *EmbedWriter) writeResponse(data []byte) (int, error) {
var embedResponse api.EmbedResponse
err := json.Unmarshal(data, &embedResponse)
if err != nil {
return 0, err
}
w.ResponseWriter.Header().Set("Content-Type", "application/json")
err = json.NewEncoder(w.ResponseWriter).Encode(toEmbeddingList(w.model, embedResponse))
if err != nil {
return 0, err
}

11
openai/openai_test.go

@ -12,13 +12,16 @@ import (
"time"
"github.com/gin-gonic/gin"
"github.com/ollama/ollama/api"
"github.com/stretchr/testify/assert"
"github.com/ollama/ollama/api"
)
const prefix = `data:image/jpeg;base64,`
const image = `iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNk+A8AAQUBAScY42YAAAAASUVORK5CYII=`
const imageURL = prefix + image
const (
prefix = `data:image/jpeg;base64,`
image = `iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNk+A8AAQUBAScY42YAAAAASUVORK5CYII=`
imageURL = prefix + image
)
func prepareRequest(req *http.Request, body any) {
bodyBytes, _ := json.Marshal(body)

12
parser/parser_test.go

@ -82,7 +82,7 @@ TEMPLATE """ {{ if .System }}<|start_header_id|>system<|end_header_id|>
}
func TestParseFileFrom(t *testing.T) {
var cases = []struct {
cases := []struct {
input string
expected []Command
err error
@ -185,7 +185,7 @@ BADCOMMAND param1 value1
}
func TestParseFileMessages(t *testing.T) {
var cases = []struct {
cases := []struct {
input string
expected []Command
err error
@ -276,7 +276,7 @@ MESSAGE system`,
}
func TestParseFileQuoted(t *testing.T) {
var cases = []struct {
cases := []struct {
multiline string
expected []Command
err error
@ -430,7 +430,7 @@ TEMPLATE """
}
func TestParseFileParameters(t *testing.T) {
var cases = map[string]struct {
cases := map[string]struct {
name, value string
}{
"numa true": {"numa", "true"},
@ -491,7 +491,7 @@ func TestParseFileParameters(t *testing.T) {
}
func TestParseFileComments(t *testing.T) {
var cases = []struct {
cases := []struct {
input string
expected []Command
}{
@ -516,7 +516,7 @@ FROM foo
}
func TestParseFileFormatParseFile(t *testing.T) {
var cases = []string{
cases := []string{
`
FROM foo
ADAPTER adapter1

3
progress/bar.go

@ -6,8 +6,9 @@ import (
"strings"
"time"
"github.com/ollama/ollama/format"
"golang.org/x/term"
"github.com/ollama/ollama/format"
)
type Bar struct {

4
readline/buffer.go

@ -13,7 +13,7 @@ type Buffer struct {
DisplayPos int
Pos int
Buf *arraylist.List
//LineHasSpace is an arraylist of bools to keep track of whether a line has a space at the end
// LineHasSpace is an arraylist of bools to keep track of whether a line has a space at the end
LineHasSpace *arraylist.List
Prompt *Prompt
LineWidth int
@ -56,7 +56,7 @@ func (b *Buffer) GetLineSpacing(line int) bool {
func (b *Buffer) MoveLeft() {
if b.Pos > 0 {
//asserts that we retrieve a rune
// asserts that we retrieve a rune
if e, ok := b.Buf.Get(b.Pos - 1); ok {
if r, ok := e.(rune); ok {
rLength := runewidth.RuneWidth(r)

4
readline/errors.go

@ -4,9 +4,7 @@ import (
"errors"
)
var (
ErrInterrupt = errors.New("Interrupt")
)
var ErrInterrupt = errors.New("Interrupt")
type InterruptError struct {
Line []rune

6
readline/term_linux.go

@ -7,8 +7,10 @@ import (
"unsafe"
)
const tcgets = 0x5401
const tcsets = 0x5402
const (
tcgets = 0x5401
tcsets = 0x5402
)
func getTermios(fd uintptr) (*Termios, error) {
termios := new(Termios)

6
server/download.go

@ -28,8 +28,10 @@ import (
const maxRetries = 6
var errMaxRetriesExceeded = errors.New("max retries exceeded")
var errPartStalled = errors.New("part stalled")
var (
errMaxRetriesExceeded = errors.New("max retries exceeded")
errPartStalled = errors.New("part stalled")
)
var blobDownloadManager sync.Map

6
server/images.go

@ -828,7 +828,7 @@ func PushModel(ctx context.Context, name string, regOpts *registryOptions, fn fu
fn(api.ProgressResponse{Status: "retrieving manifest"})
if mp.ProtocolScheme == "http" && !regOpts.Insecure {
return fmt.Errorf("insecure protocol http")
return errors.New("insecure protocol http")
}
manifest, _, err := GetManifest(mp)
@ -895,7 +895,7 @@ func PullModel(ctx context.Context, name string, regOpts *registryOptions, fn fu
}
if mp.ProtocolScheme == "http" && !regOpts.Insecure {
return fmt.Errorf("insecure protocol http")
return errors.New("insecure protocol http")
}
fn(api.ProgressResponse{Status: "pulling manifest"})
@ -1010,7 +1010,7 @@ func GetSHA256Digest(r io.Reader) (string, int64) {
return fmt.Sprintf("sha256:%x", h.Sum(nil)), n
}
var errUnauthorized = fmt.Errorf("unauthorized: access denied")
var errUnauthorized = errors.New("unauthorized: access denied")
// getTokenSubject returns the subject of a JWT token, it does not validate the token
func getTokenSubject(token string) string {

4
server/manifest.go

@ -2,9 +2,9 @@ package server
import (
"crypto/sha256"
"encoding/hex"
"encoding/json"
"errors"
"fmt"
"io"
"log/slog"
"os"
@ -88,7 +88,7 @@ func ParseNamedManifest(n model.Name) (*Manifest, error) {
m.filepath = p
m.fi = fi
m.digest = fmt.Sprintf("%x", sha256sum.Sum(nil))
m.digest = hex.EncodeToString(sha256sum.Sum(nil))
return &m, nil
}

2
server/manifest_test.go

@ -14,7 +14,7 @@ func createManifest(t *testing.T, path, name string) {
t.Helper()
p := filepath.Join(path, "manifests", name)
if err := os.MkdirAll(filepath.Dir(p), 0755); err != nil {
if err := os.MkdirAll(filepath.Dir(p), 0o755); err != nil {
t.Fatal(err)
}

1
server/model_test.go

@ -9,6 +9,7 @@ import (
"testing"
"github.com/google/go-cmp/cmp"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/template"
)

1
server/prompt_test.go

@ -6,6 +6,7 @@ import (
"testing"
"github.com/google/go-cmp/cmp"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/template"
)

14
server/routes.go

@ -55,8 +55,10 @@ func init() {
gin.SetMode(mode)
}
var errRequired = errors.New("is required")
var errBadTemplate = errors.New("template error")
var (
errRequired = errors.New("is required")
errBadTemplate = errors.New("template error")
)
func modelOptions(model *Model, requestOpts map[string]interface{}) (api.Options, error) {
opts := api.DefaultOptions()
@ -369,7 +371,6 @@ func (s *Server) EmbedHandler(c *gin.Context) {
input[i] = s
}
embeddings, err := r.Embed(c.Request.Context(), input)
if err != nil {
slog.Error("embedding generation failed", "error", err)
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to generate embedding"})
@ -430,7 +431,6 @@ func (s *Server) EmbeddingsHandler(c *gin.Context) {
}
embeddings, err := r.Embed(c.Request.Context(), []string{req.Prompt})
if err != nil {
slog.Info(fmt.Sprintf("embedding generation failed: %v", err))
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to generate embedding"})
@ -556,7 +556,7 @@ func checkNameExists(name model.Name) error {
for n := range names {
if strings.EqualFold(n.Filepath(), name.Filepath()) && n != name {
return fmt.Errorf("a model with that name already exists")
return errors.New("a model with that name already exists")
}
}
@ -729,7 +729,7 @@ func GetModelInfo(req api.ShowRequest) (*api.ShowResponse, error) {
n := model.ParseName(req.Model)
if !n.IsValid() {
return nil, fmt.Errorf("invalid model name")
return nil, errors.New("invalid model name")
}
manifest, err := ParseNamedManifest(n)
@ -993,7 +993,7 @@ func allowedHost(host string) bool {
return true
}
var tlds = []string{
tlds := []string{
"localhost",
"local",
"internal",

7
server/routes_create_test.go

@ -13,6 +13,7 @@ import (
"testing"
"github.com/gin-gonic/gin"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/llm"
)
@ -489,7 +490,7 @@ func TestCreateTemplateSystem(t *testing.T) {
Modelfile: fmt.Sprintf("FROM %s\nTEMPLATE {{ .Prompt", createBinFile(t, nil, nil)),
Stream: &stream,
})
if w.Code != http.StatusBadRequest {
t.Fatalf("expected status code 400, actual %d", w.Code)
}
@ -501,7 +502,7 @@ func TestCreateTemplateSystem(t *testing.T) {
Modelfile: fmt.Sprintf("FROM %s\nTEMPLATE {{ if .Prompt }}", createBinFile(t, nil, nil)),
Stream: &stream,
})
if w.Code != http.StatusBadRequest {
t.Fatalf("expected status code 400, actual %d", w.Code)
}
@ -513,7 +514,7 @@ func TestCreateTemplateSystem(t *testing.T) {
Modelfile: fmt.Sprintf("FROM %s\nTEMPLATE {{ Prompt }}", createBinFile(t, nil, nil)),
Stream: &stream,
})
if w.Code != http.StatusBadRequest {
t.Fatalf("expected status code 400, actual %d", w.Code)
}

1
server/routes_delete_test.go

@ -9,6 +9,7 @@ import (
"testing"
"github.com/gin-gonic/gin"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/types/model"
)

1
server/routes_list_test.go

@ -8,6 +8,7 @@ import (
"testing"
"github.com/gin-gonic/gin"
"github.com/ollama/ollama/api"
)

1
server/routes_test.go

@ -333,7 +333,6 @@ func Test_Routes(t *testing.T) {
t.Fatalf("expected content type application/json; charset=utf-8, got %s", contentType)
}
_, err := io.ReadAll(resp.Body)
if err != nil {
t.Fatal(err)
}

2
server/sched.go

@ -58,7 +58,7 @@ var defaultModelsPerGPU = 3
// we'll back off down to 1 to try to get it to fit
var defaultParallel = 4
var ErrMaxQueue = fmt.Errorf("server busy, please try again. maximum pending requests exceeded")
var ErrMaxQueue = errors.New("server busy, please try again. maximum pending requests exceeded")
func InitScheduler(ctx context.Context) *Scheduler {
maxQueue := envconfig.MaxQueue()

18
server/sched_test.go

@ -3,23 +3,25 @@ package server
import (
"bytes"
"context"
"fmt"
"errors"
"log/slog"
"os"
"testing"
"time"
"github.com/stretchr/testify/require"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/app/lifecycle"
"github.com/ollama/ollama/format"
"github.com/ollama/ollama/gpu"
"github.com/ollama/ollama/llm"
"github.com/stretchr/testify/require"
)
func init() {
func TestMain(m *testing.M) {
os.Setenv("OLLAMA_DEBUG", "1")
lifecycle.InitLogging()
os.Exit(m.Run())
}
func TestInitScheduler(t *testing.T) {
@ -46,7 +48,7 @@ func TestLoad(t *testing.T) {
}
// Fail to load model first
s.newServerFn = func(gpus gpu.GpuInfoList, model string, ggml *llm.GGML, adapters []string, projectors []string, opts api.Options, numParallel int) (llm.LlamaServer, error) {
return nil, fmt.Errorf("something failed to load model blah")
return nil, errors.New("something failed to load model blah")
}
gpus := gpu.GpuInfoList{}
s.load(req, ggml, gpus, 0)
@ -75,7 +77,7 @@ func TestLoad(t *testing.T) {
}
req.model.ModelPath = "dummy_model_path"
server.waitResp = fmt.Errorf("wait failure")
server.waitResp = errors.New("wait failure")
s.load(req, ggml, gpus, 0)
select {
case err := <-req.errCh:
@ -600,7 +602,7 @@ func TestNeedsReload(t *testing.T) {
resp = runner.needsReload(ctx, req)
require.True(t, resp)
req.opts.NumBatch = runner.Options.NumBatch
llm.pingResp = fmt.Errorf("foo")
llm.pingResp = errors.New("foo")
resp = runner.needsReload(ctx, req)
require.True(t, resp)
llm.pingResp = nil
@ -724,15 +726,19 @@ func (s *mockLlm) WaitUntilRunning(ctx context.Context) error { return s.waitRes
func (s *mockLlm) Completion(ctx context.Context, req llm.CompletionRequest, fn func(llm.CompletionResponse)) error {
return s.completionResp
}
func (s *mockLlm) Embed(ctx context.Context, input []string) (*llm.EmbedResponse, error) {
return s.embedResp, s.embedRespErr
}
func (s *mockLlm) Tokenize(ctx context.Context, content string) ([]int, error) {
return s.tokenizeResp, s.tokenizeRespErr
}
func (s *mockLlm) Detokenize(ctx context.Context, tokens []int) (string, error) {
return s.detokenizeResp, s.detonekizeRespErr
}
func (s *mockLlm) Close() error {
s.closeCalled = true
return s.closeResp

6
server/upload.go

@ -12,13 +12,15 @@ import (
"net/http"
"net/url"
"os"
"strconv"
"sync"
"sync/atomic"
"time"
"golang.org/x/sync/errgroup"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/format"
"golang.org/x/sync/errgroup"
)
var blobUploadManager sync.Map
@ -212,7 +214,7 @@ func (b *blobUpload) Run(ctx context.Context, opts *registryOptions) {
func (b *blobUpload) uploadPart(ctx context.Context, method string, requestURL *url.URL, part *blobUploadPart, opts *registryOptions) error {
headers := make(http.Header)
headers.Set("Content-Type", "application/octet-stream")
headers.Set("Content-Length", fmt.Sprintf("%d", part.Size))
headers.Set("Content-Length", strconv.FormatInt(part.Size, 10))
if method == http.MethodPatch {
headers.Set("X-Redirect-Uploads", "1")

3
template/template.go

@ -15,8 +15,9 @@ import (
"text/template/parse"
"github.com/agnivade/levenshtein"
"github.com/ollama/ollama/api"
"golang.org/x/exp/maps"
"github.com/ollama/ollama/api"
)
//go:embed index.json

1
template/template_test.go

@ -12,6 +12,7 @@ import (
"testing"
"github.com/google/go-cmp/cmp"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/llm"
)

6
types/errtypes/errtypes.go

@ -6,8 +6,10 @@ import (
"strings"
)
const UnknownOllamaKeyErrMsg = "unknown ollama key"
const InvalidModelNameErrMsg = "invalid model name"
const (
UnknownOllamaKeyErrMsg = "unknown ollama key"
InvalidModelNameErrMsg = "invalid model name"
)
// TODO: This should have a structured response from the API
type UnknownOllamaKey struct {

2
types/model/name.go

@ -258,7 +258,7 @@ func (n Name) IsValid() bool {
// IsFullyQualified returns true if all parts of the name are present and
// valid without the digest.
func (n Name) IsFullyQualified() bool {
var parts = []string{
parts := []string{
n.Host,
n.Namespace,
n.Model,

Loading…
Cancel
Save