github turboderp-org/exllamav3 v1.5.1
1.5.1

3 hours ago
  • Add KimiLinearForCausalLM
  • Add DFlash2
  • TP support for Qwen3.8-Flash-Next, GLM5.3, DeepseekV3/V4
  • MoE optimizations
  • Fractional-trellis quantization mode
  • Self-calibration pipeline improvements (including highly experimental YAQA support)
  • Fix some memory leaks
  • Fix EXL3_MOE_PINNED_ARENA on Windows and Conda
  • Other optimizations and bugfixes

Full Changelog: v1.5.0...v1.5.1

Don't miss a new exllamav3 release

NewReleases is sending notifications on new releases.