AI-ML
Ollama v0.30.1
RESUMEN
What's Changed feat(launch): show and auto-install Cline CLI by @hoyyeva in log template details to aid troubleshooting by @dhiltgen in * cmd/launch: add Qwen code integration by @hoyyeva in
Descripción Detallada
What's Changed feat(launch): show and auto-install Cline CLI by @hoyyeva in log template details to aid troubleshooting by @dhiltgen in cmd/launch: add Qwen code integration by @hoyyeva in launch: fix opencode local model limits by @dhiltgen in llm: include cached prompt tokens in llama-server counts by @dhiltgen in Harden app markdown URL handling by @dhiltgen in discover: allow Radeon 8060S iGPU by default by @dhiltgen in llm: detect llama-server load stalls from output by @dhiltgen in More harden app markdown URL handling by @dhiltgen in llama.cpp version update by @dhiltgen in * launch: isolate Codex launch configuration by @ParthSareen in Full Changelog:
Explicación con IA
Genera un resumen en lenguaje claro de los cambios de este release.
Releases Relacionados
AI-ML
Ollama v0.32.5
## What's Changed * Fixed an MLX Metal bug that could reduce output quality for NVFP4 models, particularly Laguna. **Full Changelog**: https://github.com/ollama/ollama/compare/v0.32.4...v0.32.5
AI-ML
Ollama v0.32.4
## What's Changed - Support Laguna on Apple GPUs via the MLX engine - Quantize draft-model output heads at the requested type when creating speculative-decoding drafts. - Fixed Qwen3 MoE decoding for differently-quantized experts, plus faster packed gate/up projection (~4–9% on M5 Max). **Full
AI-ML