v0.1.6

What's Changed

• Causal Masking and model selection from .toml files by @EricLBuehler in #278
• Remove sliding window mask from quantized phi3 by @EricLBuehler in #280
• Fix Causal Mask by @EricLBuehler in #282
• Fix mask caching by @EricLBuehler in #283
• More intelligent scheduler by @EricLBuehler in #279
• Use warn! macro by @EricLBuehler in #289
• Use a public repo for tests tokenizer.json by @EricLBuehler in #290
• Implement Speculative Decoding by @EricLBuehler in #242
• Add X-LoRA support for GGUF by @EricLBuehler in #293
• Add some "senseful" fallbacks for isq by @LLukas22 in #272
• Implement dynamic LoRA swapping by @EricLBuehler in #262
• More verbose logging when loading locally by @EricLBuehler in #298
• Make speculative decoding faster without anything fancy by @EricLBuehler in #297
• fix bug with mistralrs cuda by @joshpopelka20 in #299

New Contributors

• @joshpopelka20 made their first contribution in #299

New Features

• Speculative decoding introduced
• GGUF support for Phi 3
• Dynamic LoRA adapter activation support

Full Changelog: v0.1.5...v0.1.6

v0.1.5

What's Changed

• Warmup pass for mistralrs-bench by @EricLBuehler in #270
• Fix short param conflict for LoRA by @EricLBuehler in #271
• Add build.rs to PyO3 to improve compat when extension_module by @EricLBuehler in #274
• Add the quantized phi3 model by @EricLBuehler in #276

Full Changelog: v0.1.4...v0.1.5

v0.1.4

What's Changed

• Major pipeline refactor by @EricLBuehler in #261
• docs: update README.md by @eltociear in #264
• Support EOF in interactive mode by @EricLBuehler in #267
• Fix concat in PhiRotaryEmbedding by @EricLBuehler in #268
• More organized config printing by @EricLBuehler in #269

Full Changelog: v0.1.3...v0.1.4

v0.1.3

What's Changed

• Add automatic pypi upload and docker build on release by @EricLBuehler in #255
• Update PyO3 to take dict by @EricLBuehler in #257

Full Changelog: v0.1.2...v0.1.3

v0.1.2

New features

• Initial async integrations (#198, #236) thanks to @lucasavila00.
• More flexibility with bos and eos tokens (#248)
• Intermediate loading for ISQ models on CPU (#229)
• Fixed Phi 3 128k finally, it is fully working now! (#251)

Changelog

• Update README.md by @KPCOFGS in #224
• Fix api_dir_list! and show better error by @EricLBuehler in #225
• Default to none when cannot find token by @EricLBuehler in #226
• docs: update ADAPTER_MODELS.md by @eltociear in #227
• Fix debug log timing of first token by @lucasavila00 in #231
• Implement intermediate loading for ISQ on CPU by @EricLBuehler in #229
• Async sampling by @lucasavila00 in #198
• Fix quantized example by @lucasavila00 in #237
• Source bos, eos tokens from generation_config.json by @EricLBuehler in #243
• Sliding window for phi3 by @EricLBuehler in #244
• Fix docker images by @LLukas22 in #249
• Remove forced max seq len for llama models by @EricLBuehler in #250
• Fix Phi3 128k finally: use position ids to switch between short/long scaling by @EricLBuehler in #251
• Update README.md by @criminact in #253
• Async channels by @lucasavila00 in #236

New Contributors

• @KPCOFGS made their first contribution in #224
• @eltociear made their first contribution in #227
• @criminact made their first contribution in #253

Full Changelog: v0.1.0...v0.1.2

v0.1.0

Update version