turboderp-org/exllamav3 v1.4.5

1.4.5

on GitHub

• Support Glm5NextForConditionalGeneration (GLM5.3-Flash)
• Support Qwen4ExpForConditionalGeneration (Qwen3.8-Flash-Next)
• Improved MoE MTP performance
• Slab allocation for MoE layers to avoid wasted VRAM for badly aligned expert tensor shapes
• Work around Triton race condition (autotuner: 'NoneType' object is not a mapping error)
• Fix Unigram tokenizers
• Other bugfixes and QoL improvements

Full Changelog: v1.4.4...v1.4.5