Files
ollama37/server/create_test.go
Shang Chieh Tseng ef14fb5b26 Sync with upstream ollama/ollama and restore Tesla K80 (compute 3.7) support
This commit represents a complete rework after pulling the latest changes from
official ollama/ollama repository and re-applying Tesla K80 compatibility patches.

## Key Changes

### CUDA Compute Capability 3.7 Support (Tesla K80)
- Added sm_37 (compute 3.7) to CMAKE_CUDA_ARCHITECTURES in CMakeLists.txt
- Updated CMakePresets.json to include compute 3.7 in "CUDA 11" preset
- Using 37-virtual (PTX with JIT compilation) for maximum compatibility

### Legacy Toolchain Compatibility
- **NVIDIA Driver**: 470.256.02 (last version supporting Kepler/K80)
- **CUDA Version**: 11.4.4 (last CUDA 11.x supporting compute 3.7)
- **GCC Version**: 10.5.0 (required by CUDA 11.4 host_config.h)

### CPU Architecture Trade-offs
Due to GCC 10.5 limitation, sacrificed newer CPU optimizations:
- Alderlake CPU variant enabled WITHOUT AVX_VNNI (requires GCC 11+)
- Still supports: SSE4.2, AVX, F16C, AVX2, BMI2, FMA
- Performance impact: ~3-7% on newer CPUs (acceptable for K80 compatibility)

### Build System Updates
- Modified ml/backend/ggml/ggml/src/ggml-cuda/CMakeLists.txt for compute 3.7
- Added -Wno-deprecated-gpu-targets flag to suppress warnings
- Updated ml/backend/ggml/ggml/src/CMakeLists.txt for Alderlake without AVX_VNNI

### Upstream Sync
Merged latest llama.cpp changes including:
- Enhanced KV cache management with ISWA and hybrid memory support
- Improved multi-modal support (mtmd framework)
- New model architectures (Gemma3, Llama4, Qwen3, etc.)
- GPU backend improvements for CUDA, Metal, and ROCm
- Updated quantization support and GGUF format handling

### Documentation
- Updated CLAUDE.md with comprehensive build instructions
- Documented toolchain constraints and CPU architecture trade-offs
- Removed outdated CI/CD workflows (tesla-k80-*.yml)
- Cleaned up temporary development artifacts

## Rationale

This fork maintains Tesla K80 GPU support (compute 3.7) which was dropped in
official Ollama due to legacy driver/CUDA requirements. The toolchain constraint
creates a deadlock:
- K80 → Driver 470 → CUDA 11.4 → GCC 10 → No AVX_VNNI

We accept the loss of cutting-edge CPU optimizations to enable running modern
LLMs on legacy but still capable Tesla K80 hardware (12GB VRAM per GPU).

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-05 14:03:05 +08:00

258 lines
5.7 KiB
Go

package server
import (
"bytes"
"encoding/binary"
"errors"
"os"
"path/filepath"
"strings"
"testing"
"github.com/ollama/ollama/api"
)
func TestConvertFromSafetensors(t *testing.T) {
t.Setenv("OLLAMA_MODELS", t.TempDir())
// Helper function to create a new layer and return its digest
makeTemp := func(content string) string {
l, err := NewLayer(strings.NewReader(content), "application/octet-stream")
if err != nil {
t.Fatalf("Failed to create layer: %v", err)
}
return l.Digest
}
// Create a safetensors compatible file with empty JSON content
var buf bytes.Buffer
headerSize := int64(len("{}"))
binary.Write(&buf, binary.LittleEndian, headerSize)
buf.WriteString("{}")
model := makeTemp(buf.String())
config := makeTemp(`{
"architectures": ["LlamaForCausalLM"],
"vocab_size": 32000
}`)
tokenizer := makeTemp(`{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
]
}`)
tests := []struct {
name string
filePath string
wantErr error
}{
// Invalid
{
name: "InvalidRelativePathShallow",
filePath: filepath.Join("..", "file.safetensors"),
wantErr: errFilePath,
},
{
name: "InvalidRelativePathDeep",
filePath: filepath.Join("..", "..", "..", "..", "..", "..", "data", "file.txt"),
wantErr: errFilePath,
},
{
name: "InvalidNestedPath",
filePath: filepath.Join("dir", "..", "..", "..", "..", "..", "other.safetensors"),
wantErr: errFilePath,
},
{
name: "AbsolutePathOutsideRoot",
filePath: filepath.Join(os.TempDir(), "model.safetensors"),
wantErr: errFilePath, // Should fail since it's outside tmpDir
},
{
name: "ValidRelativePath",
filePath: "model.safetensors",
wantErr: nil,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
// Create the minimum required file map for convertFromSafetensors
files := map[string]string{
tt.filePath: model,
"config.json": config,
"tokenizer.json": tokenizer,
}
_, err := convertFromSafetensors(files, nil, false, func(resp api.ProgressResponse) {})
if (tt.wantErr == nil && err != nil) ||
(tt.wantErr != nil && err == nil) ||
(tt.wantErr != nil && !errors.Is(err, tt.wantErr)) {
t.Errorf("convertFromSafetensors() error = %v, wantErr %v", err, tt.wantErr)
}
})
}
}
func TestRemoteURL(t *testing.T) {
tests := []struct {
name string
input string
expected string
hasError bool
}{
{
name: "absolute path",
input: "/foo/bar",
expected: "http://localhost:11434/foo/bar",
hasError: false,
},
{
name: "absolute path with cleanup",
input: "/foo/../bar",
expected: "http://localhost:11434/bar",
hasError: false,
},
{
name: "root path",
input: "/",
expected: "http://localhost:11434/",
hasError: false,
},
{
name: "host without scheme",
input: "example.com",
expected: "http://example.com:11434",
hasError: false,
},
{
name: "host with port",
input: "example.com:8080",
expected: "http://example.com:8080",
hasError: false,
},
{
name: "full URL",
input: "https://example.com:8080/path",
expected: "https://example.com:8080/path",
hasError: false,
},
{
name: "full URL with path cleanup",
input: "https://example.com:8080/path/../other",
expected: "https://example.com:8080/other",
hasError: false,
},
{
name: "ollama.com special case",
input: "ollama.com",
expected: "https://ollama.com:443",
hasError: false,
},
{
name: "http ollama.com special case",
input: "http://ollama.com",
expected: "https://ollama.com:443",
hasError: false,
},
{
name: "URL with only host",
input: "http://example.com",
expected: "http://example.com:11434",
hasError: false,
},
{
name: "URL with root path cleaned",
input: "http://example.com/",
expected: "http://example.com:11434",
hasError: false,
},
{
name: "invalid URL",
input: "http://[::1]:namedport", // invalid port
expected: "",
hasError: true,
},
{
name: "empty string",
input: "",
expected: "http://localhost:11434",
hasError: false,
},
{
name: "host with scheme but no port",
input: "http://localhost",
expected: "http://localhost:11434",
hasError: false,
},
{
name: "complex path cleanup",
input: "/a/b/../../c/./d",
expected: "http://localhost:11434/c/d",
hasError: false,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
result, err := remoteURL(tt.input)
if tt.hasError {
if err == nil {
t.Errorf("expected error but got none")
}
return
}
if err != nil {
t.Errorf("unexpected error: %v", err)
return
}
if result != tt.expected {
t.Errorf("expected %q, got %q", tt.expected, result)
}
})
}
}
func TestRemoteURL_Idempotent(t *testing.T) {
// Test that applying remoteURL twice gives the same result as applying it once
testInputs := []string{
"/foo/bar",
"example.com",
"https://example.com:8080/path",
"ollama.com",
"http://localhost:11434",
}
for _, input := range testInputs {
t.Run(input, func(t *testing.T) {
firstResult, err := remoteURL(input)
if err != nil {
t.Fatalf("first call failed: %v", err)
}
secondResult, err := remoteURL(firstResult)
if err != nil {
t.Fatalf("second call failed: %v", err)
}
if firstResult != secondResult {
t.Errorf("function is not idempotent: first=%q, second=%q", firstResult, secondResult)
}
})
}
}