0.0.5

• Add filter interface
• Add Formatron support (JSON/KBNF grammar etc.)
• Support Ernie 4.5 architecture
• Support SmolLM3 architecture
• Support Exaone4 architecture
• Improve Cohere2 support (fixes support for Command-A)
• Fix compatibility with certain Pixtral preprocessors
• Fix excessive virtual memory usage with large generator queues on Windows
• Add facilities for manually mixing/optimizing quants
• Add MMLU eval script
• Various other fixes, improvements and optimizations

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

0.0.4

• Vision support
• Support MiMoForCausalLM (no MTP)
• Support Gemma3ForConditionalGeneration
• Support Gemma3ForCausalLM
• Support Mistral3ForConditionalGeneration (Mistral 3.1)
• Support Dots1ForCausalLM (dots.llm1)
• Add Transformers integration
• Faster tokenizer initialization
• Various fixes

Full Changelog: v0.0.3...v0.0.4

0.0.3

• Support Mixtral architecture
• Support Gemma3 architecture (text only)
• Fixed support for Command-R+
• Return probs and top probs from generator
• Defrag for generator
• Many bugfixes
• Many performance improvements
• A bunch of new eval and test functionality

Full Changelog: v0.0.2...v0.0.3

0.0.2

• Adds Qwen3MoE support
• Various bugfixes and optimizations

Full Changelog: v0.0.1...v0.0.2

0.0.1

Actions: Add build action

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>