v5.0.2

What's Changed

Re-issuing v5.0.1 to fix a pypi release bug.

• Moving HumanEval to pypi (@ramkrishna2910)
• Adds std dev for oga-bench (@amd-pworfolk)
• Updates build status monitor to change update frequency (@danielholanda)
• Fix linter issue (@ramkrishna2910)
• Fix llama.cpp issue introduced by their breaking change (@jeremyfowers)
• Polish llama.cpp implementation (@ramkrishna2910)
• Minor changes fixing onnxruntime_genai issue and input_path by @apsonawane in #267

New Contributors

• @apsonawane made their first contribution in #267

Full Changelog: v5.0.0...v5.0.2

v5.0.1

What's Changed

• Moving HumanEval to pypi (@ramkrishna2910)
• Adds std dev for oga-bench (@amd-pworfolk)
• Updates build status monitor to change update frequency (@danielholanda)
• Fix linter issue (@ramkrishna2910)
• Fix llama.cpp issue introduced by their breaking change (@jeremyfowers)
• Polish llama.cpp implementation (@ramkrishna2910)
• Minor changes fixing onnxruntime_genai issue and input_path by @apsonawane in #267

New Contributors

• @apsonawane made their first contribution in #267

Full Changelog: v5.0.0...v5.0.1

v5.0.0

What's Changed

• Improve documentation and LLM status clarity by @jeremyfowers in #261
• Move llm source code into src/lemonade dir. Add HumanEval. by @jeremyfowers in #262
• Adds llamacpp benchmarking support by @ramkrishna2910 in #263

Full Changelog: v4.0.11...v5.0.0

v4.0.11

What's Changed

• Hotfix: monitor progress bug by @jeremyfowers in #259

Full Changelog: v4.0.10...v4.0.11

v4.0.10

What's Changed

• Update ort_genai_hybrid.md by @jeremyfowers in #256
• Standardize Timestamps to Fixed Time Zone in TKML Runs by @danielholanda in #257
• Allow tools to display percent progress in the monitor by @jeremyfowers in #258

Full Changelog: v4.0.9...v4.0.10

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