AI-ML
Ollama v0.31.2
RESUMEN
What's Changed ci: avoid unbounded parallelism by @dhiltgen in fix cuda toolkit lookup and parallel by @MarkWard0110 in * docs(cloud): update retirement list by @mxyng in
Descripción Detallada
What's Changed ci: avoid unbounded parallelism by @dhiltgen in fix cuda toolkit lookup and parallel by @MarkWard0110 in docs(cloud): update retirement list by @mxyng in discover: fall back to standard CUDA when the JetPack runner is absent by @kevinpark1217 in agent: harness core by @ParthSareen in llama: clean up dead code from llama-server work by @dhiltgen in rocm: remove no longer supported devices by @dhiltgen in compat: use UTF-8-safe file open by @dhiltgen in llama: enable FA on CUDA CC 6.x GPUs by @dhiltgen in mlx: x/create rewrite by @pdevine in llama.cpp update by @dhiltgen in server: remove OLLAMA_EXPERIMENT=client2 by @mxyng in mlx: update to de7b4ed9 by @dhiltgen in New Contributors @kevinpark1217 made their first contribution in Full Changelog:
Explicación con IA
Genera un resumen en lenguaje claro de los cambios de este release.
Releases Relacionados
AI-ML
Ollama v0.31.1
## Faster Gemma 4 on Apple Silicon <img width="1037" height="485" alt="Screenshot 2026-06-30 at 5 25 29 PM" src="https://github.com/user-attachments/assets/547d5076-090f-43c4-a661-938e11abc955" /> Gemma 4 is now significantly faster in Ollama on Apple Silicon, generating tokens nearly 90% fast
AI-ML
Ollama v0.30.12
## What's Changed * tools: ignore braces inside JSON strings when detecting tool call end by @aditya-786 in https://github.com/ollama/ollama/pull/16937 * mlx: bump dependency by @dhiltgen in https://github.com/ollama/ollama/pull/16935 * llama.cpp update by @dhiltgen in https://github.com/ollama/o