v0.2.1

What's Changed

• Temporary fix for stablecode and starcoder on mac by @ravenscroftj in #67

Full Changelog: v0.2.0...v0.2.1

v0.2.0

What's Changed

• New: Turbopilot now supports full GPU offloading via CUDA and OpenCL by @ravenscroftj in #55
• New: Turbopilot now supports StableCode models by @ravenscroftj in #43
• New: Turbopilot is now interoperable with the Huggingface VSCode plugin by @ravenscroftj in #44
• New: End-user control of generation temperature and top-p via command line arguments by @ravenscroftj in #52
• New: Exposed batch size flag via cli by @ravenscroftj in #59
• New: Added debug log level and added timings to model outputs by @ravenscroftj in #54
• Fix: incorrect instructions in model docs by @aperullo in #57
• Fix: prevent crashing of model due to multiple parallel requests by using locking @ravenscroftj in #58
• Change: moved from alpine to ubuntu in Dockerfile.default by @nvtienanh in #60
• Fix: download link on MODELS.md by @c01o in #61
• Change: Implement better docker builds by @ravenscroftj in #62

New Contributors

• @aperullo made their first contribution in #57
• @nvtienanh made their first contribution in #60
• @c01o made their first contribution in #61

Full Changelog: v0.1.0...v0.2.0

v0.1.0

What's Changed

• Refactored codebase - now a single unified turbopilot binary that provides support for codegen and starcoder style models.
• Support for starcoder, wizardcoder and santacoder models
• Support for CUDA 11 and 12

Full Changelog: v0.0.5...v0.1.0

Version 0.0.5

What's Changed

• Turbopilot now supports CUDA which significantly accelerates inference for long prompts on machines with NVIDIA cards builds by @ravenscroftj in #27
• Turbopilot now comes with prebuilt windows binaries by @ravenscroftj in #29
• Added links to download pre-converted and pre-quantized CodeGen mono models. by @virtualramblas and @CRD716 in #18 and #21

New Contributors

• @virtualramblas made their first contribution in #18
• @CRD716 made their first contribution in #21
• @ravenscroftj made their first contribution in #27

Full Changelog: v0.0.4...v0.0.5

Version 0.0.4

• Added multi-threaded server support which should prevent health checks aimed at GET / from failing during prediction.
• Separated autocomplete lambda into a separate C++ function so that it can be bound to /v1/completions, /v1/engines/copilot-codex/completions and /v1/engines/codegen/completions
• Removed model from completion input as required param which stops the official copilot plugin from freaking out
• Integrate latest changes from upstream ggml including some fixes for ARM NEON processor
• Added Mac "universal binary" builds as part of CI
• Support for fork of vscode-fauxpilot with a progress indicator is now available (PR is open upstream, please react/vote for it) vscode-fauxcode now supports progress indication

V0.0.3

• Added 350M parameter codegen model to Google Drive folder
• Added multi-arch docker images so that users can now directly run on Apple silicon and even raspberry pi 4
• Now support pre-tokenized inputs passed into the API from a Python tokenizer (thanks to @thakkarparth007 for their PR - ravenscroftj/ggml#2)

0.0.2

What's Changed

• Project now builds on Mac OS (Thanks to @Dimitrije-V for their PR ravenscroftj/ggml#1 and @dabdine for contributing some clearer Mac build instructions)
• Fix inability to load vocab.json on converting the 16B model due to encoding of the file not being set by @swanserquack in #5
• Improve performance of model by incorporating changes to GGML library from @ggerganov

New Contributors

• @swanserquack made their first contribution in #5

Full Changelog: 0.0.1...0.0.2

Version 0.0.1

• Initial release of Turbo Pilot