omlx · Issues· 1372 open

Add mlx-lm architecture support for xing4_0 (XingChen-AGI/Xing4.0-29B-A4B) — oQ fails with "sensitivity measurement produced no scores"

Support Prism ML Hadamard packs (Ternary Bonsai 2 27B, MLX 2-bit): dispatch to the pack's bundled loader + register its MODEL_CONFIG format

Can mlx-lm/mlx-vlm be kept up-to-date?

The model file size displayed on the downloader page is incorrect

Broken Cache Management

Decode throughput decays ~3.2x with server uptime on qwen4_exp (M3 Ultra): 20.5 tok/s after ~10h vs 66.5 tok/s on a fresh process

Concurrent cross-model request handling breaks when memory fits only one model

Bonsai/t5 load patch is installed for every 2-bit checkpoint, and no test covers that path

macOS 27: long-context inference 10x slower than macOS 26.6 (even after HOST_VM_INFO64 fix)

macOS 27: periodic Metal cache-clear drain hits kIOGPUCommandBufferCallbackErrorTimeout, then the SubmissionsIgnored penalty box the engine cannot self-recover from (0.5.7, M3 Ultra)

PDF processing engine not working

SSD prefix cache never stores on qwen4_exp hybrid: available_boundaries=0 while boundary snapshots are enabled

TurboQuant KV cache (4-bit) silently corrupts detail retrieval for requests that hit the prefix cache

[Feature Request] Native macOS menu-bar observability for inference workloads

Server dying with "[METAL] Command buffer execution failed: Caused GPU Timeout Error "