github turboderp-org/exllamav3 v0.0.4
0.0.4

latest releases: v1.6.1, v1.6.0, v1.5.4...
16 months ago
  • 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

Don't miss a new exllamav3 release

NewReleases is sending notifications on new releases.