Skip to content

Releases: dzivkovi/vllm-huggingface-bridge

v1.0.1 - Streamlined Documentation

29 Sep 15:43
@dzivkovi dzivkovi
v1.0.1
1525aa7

Choose a tag to compare

View all tags
v1.0.1 - Streamlined Documentation Latest
Latest

What's Changed

🎯 Documentation Overhaul

  • Reduced documentation from 10 files to 4 focused guides (85% reduction)
  • Each doc now answers ONE clear user question
  • Removed internal/developer docs from user-facing folder
  • Following "less is more" principle

🔧 Configuration Improvements

  • Fixed: customTGIEndpoint → localEndpoint throughout codebase
  • Updated default endpoint for enterprise deployment
  • Aligns with actual implementation in code

📚 Development Guidelines

  • Added Conventional Commits specification to CLAUDE.md
  • Documented proper commit prefixes (feat, fix, chore, docs)
  • Added repository-specific examples

✅ Quality Assurance

  • All 42 tests passing
  • Linting completed (npm run lint)
  • Code compilation verified
  • Package dependencies updated

📦 Impact

  • Removed: 9 files of architecture decisions, backend docs, internal processes
  • Added: 4 simple guides - installation, configuration, local setup, README
  • Net reduction: 1,039 lines of documentation overhead

📥 Installation

Download vllm-huggingface-bridge-1.0.1.vsix and install:
```bash
code --install-extension vllm-huggingface-bridge-1.0.1.vsix
```

Or drag the VSIX file into VS Code Extensions panel.

🚀 For Enterprise Users

This release includes a default enterprise endpoint configuration. Teams can now install and immediately use the extension with their internal inference servers.

Full Changelog: v1.0.0...v1.0.1

Assets 3
Loading

v1.0.0 - Stable Oasis

28 Sep 23:47
@dzivkovi dzivkovi
v1.0.0
d21cd3b

Choose a tag to compare

View all tags
v1.0.0 - Stable Oasis

🎉 First Stable Release - Production Ready!

✨ What's New

This is the first stable release of vLLM HuggingFace Bridge, a fork of the original HuggingFace VS Code extension optimized for enterprise and air-gapped deployments.

🚀 Key Features

  • Air-Gapped Operation: Complete offline functionality with local vLLM/TGI servers
  • Dual Mode Support: Seamlessly switch between local and HuggingFace cloud models
  • Enterprise Ready: Production-tested in secure environments
  • Optimized Package: 92KB (91% smaller than original)
  • Smart Token Management: Automatic allocation for small context models (2048+)
  • Enhanced Observability: Clear logging showing which model handles each request

📦 Installation

Quick Install (Recommended)

  1. Download the VSIX file below
  2. In VS Code: Ctrl+Shift+P → Extensions: Install from VSIX...
  3. Select the downloaded file and restart VS Code

Command Line

```bash
wget https://github.com/dzivkovi/vllm-huggingface-bridge/releases/download/v1.0.0/vllm-huggingface-bridge-1.0.0.vsix
code --install-extension vllm-huggingface-bridge-1.0.0.vsix
```

🔧 Configuration

For Local vLLM/TGI Servers

```json
{
"huggingface.localEndpoint": "http://localhost:8000"
}
```

For HuggingFace Cloud

  1. Open GitHub Copilot Chat
  2. Click model picker → "Manage Models..."
  3. Select "Hugging Face" provider
  4. Add your HF token

🧪 Tested With

  • VS Code 1.104+
  • vLLM 0.5+
  • TGI 2.0+
  • Various GPUs: RTX 4060, A100, H100
  • Models: DeepSeek-Coder, Qwen, Mistral, Llama

📊 Technical Improvements

  • All 42 tests passing
  • ESLint configured for pragmatic development
  • Package size reduced from 954KB to 92KB
  • Enhanced logging for debugging
  • Fixed VS Code API compatibility issues

🙏 Credits

Built on the excellent foundation of HuggingFace VS Code Chat.

📝 License

MIT License - See LICENSE.txt for details

Loading