v4.0.9

What's Changed

• Add gpu+npu amd hybrid support by @ramkrishna2910 in #252
• Add hybrid deps by @ramkrishna2910 in #253

Full Changelog: v4.0.8...v4.0.9

v4.0.8

What's Changed

• Add cuda support when loading local onnx model by @jiafatom in #249
• Add prefill tps in oga-bench by @jiafatom in #250
• Added additional system_info by @amd-pworfolk in #246
• Rev version to 4.0.8 by @ramkrishna2910 in #251

New Contributors

• @jiafatom made their first contribution in #249
• @amd-pworfolk made their first contribution in #246

Full Changelog: v4.0.7...v4.0.8

v4.0.7

What's Changed

• Add perf tools for huggingface and oga by @ramkrishna2910, @jeremyfowers in #247

Full Changelog: v4.0.6...v4.0.7

v4.0.6

What's Changed

TurnkeyML:

• Add a release process guide by @jeremyfowers in #243
• Rev ONNX and ORT deps by @jeremyfowers in #242

Turnkey-LLM:

• (@amd-pworfolk) oga-load tool will now use OGA model_builder to automatically create ONNX files for supported CPU and iGPU checkpoints. Manual download of ONNX files is no longer required.
• (@amd-pworfolk, @jeremyfowers) Improved OGA documentation for both iGPU/CPU and NPU
• (@jeremyfowers) bug fix: HF_TOKEN env var is no longer required to download AMD NPU OGA ONNX files
• (@jeremyfowers) bug fix: server /health endpoint now works with OGA (sever is now under CI testing as well)
• (@jeremyfowers) bug fix: server /ws always sends a at the end of the generation stream

Full Changelog: v4.0.5...v4.0.6

v4.0.5

What's Changed

This is a hotfix release to address ORT environment issues.

• Use platform_system to install ort-directml on Windows by @jeremyfowers in #239

Full Changelog: v4.0.4...v4.0.5

v4.0.4

What's Changed

• Prevent ORT version conflicts by @jeremyfowers in #238
• Add support for using a Llama.cpp binary and model from TurnkeyML by @gabeweisz in #234
• Update LLM server, fix bugs, and format with black by @jeremyfowers in #236

New Contributors

• @gabeweisz made their first contribution in #234

Full Changelog: v4.0.3...v4.0.4

v4.0.3

What's Changed

• Fix wmic warning by @ramkrishna2910 in #229
• Add CPU oga support and update hyperparameters by @ramkrishna2910 in #231
• Fix major CI bugs by @danielholanda in #233
• Add NPU OGA support for RyzenAI 1.3 EA by @danielholanda in #232

Full Changelog: v4.0.2...v4.0.3

v4.0.2

What's Changed

• Fixes for LLM release by @jeremyfowers in #227

Full Changelog: v4.0.1...v4.0.2

v4.0.1

This is the release that introduces TurnkeyML-LLM aka lemonade.

What's Changed

• Enable the device tests and update utils by @jeremyfowers in #224
• Turnkey-LLM (aka lemonade) by @jeremyfowers in #225

Full Changelog: v4.0.0...v4.0.1

v4.0.0

What's Changed

• Remove the refresh notice on the front readme.md by @jeremyfowers in #214
• Add build_name to stats by @danielholanda in #223
• Move run submodule out into the new devices plugin by @jeremyfowers in #222

Full Changelog: v3.0.7...v4.0.0