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

lint

Browse Source
This commit is contained in:
Michael Yang
2024-08-01 14:52:15 -07:00
parent 558a54b098
commit b732beba6a
68 changed files with 199 additions and 149 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
llm/llm.go
View File

@@ -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
View File

@@ -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
View File

@@ -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
}