Skip to content

v0.81.63

Latest

Choose a tag to compare

@github-actions github-actions released this 12 Jul 22:50

Improved

  • MoE auto-sweep leaves VRAM headroom... it measures pp512/tg128, shows live samples and saves only the final recommendation, three ncmoe steps above the tight edge when safe.
  • MTP is automatic... it activates only for GGUFs with an MTP head and offloaded MoE experts, avoiding measured regressions on full-GPU models.
  • Qwen3.5/3.6 decode uses one less Metal dispatch per GDN layer by fusing SSM_CONV with its following SiLU activation.
  • Long-prompt prefill is faster on AMD RDNA for head sizes 64/128/256/512 (up to 54% at pp4096), with no measured decode regression; quantized KV and wave64 keep Flash Attention.

Fixed

  • MoE auto-sweep no longer hangs on verbose output and now parses Metal VRAM sizes correctly.
  • BF16 decode is covered by the AMD wave64 GPU path instead of falling back to CPU.

Full Changelog: v0.81.62...v0.81.63