Tagged "inference-stability"

4 articles tagged inference-stability, 12 February 2026 to 16 September 2026. Newest first.

• Ollama 0.34.1 Stabilizes MLX Backend and GGUF Model Creation 16 September 2026

  Ollama v0.34.1 releases improved MLX memory handling for Apple Silicon, stabilizes GGUF creation workflows, and enhances repeat token detection for more reliable local inference.

• Llama.cpp Fixes Metal NORM Operations for Apple Silicon 8 August 2026

  Llama.cpp B10321 resolves critical issues with NORM and RMS_NORM operations on Apple Silicon, fixing threadgroup synchronization for row lengths that don't align with SIMD group boundaries. This ensures reliable inference on M-series chips.

• Gemma 4 GGUF Models Updated with Critical Quantization Fixes 9 April 2026

  Unsloth has released updated Gemma 4 GGUF quantizations addressing kv-cache issues and other inference problems. New versions are available for both 26B and 31B model sizes.

• Heaps Do Lie: Debugging a Memory Leak in vLLM 12 February 2026

  Mistral AI engineers share detailed technical insights into identifying and fixing a critical memory leak in vLLM inference engine.