Published event
ArtificialIntelligence
ProductUpdate
2 source(s)
v0.32.4
Summary
v0.32.4 ollama / ollama Public Notifications You must be signed in to change notification settings Fork 18k Star 182k v0.32.4 github-actions released this 25 Jul 02:22 · 219 commits to main since this release v0.32.4 64ee2f9 This commit was created on GitHub.com and signed with GitHub’s verified signature . GPG key ID: B5690EEEBB952194 Verified Learn about vigilant mode .
Why it matters
This ProductUpdate is relevant to the technology intelligence record because it involves Apple, GitHub, Qwen, Llama. The source article should remain the factual reference for follow-up coverage.
Key facts
- ollama / ollama Public Notifications You must be signed in to change notification settings Fork 18k Star 182k v0.32.4 github-actions released this 25 Jul 02:22 · 219 commits to main since this release v0.32.4 64ee2f9 This commit was created on GitHub.com and signed with GitHub’s verified signature .
- GPG key ID: B5690EEEBB952194 Verified Learn about vigilant mode .
- 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 Changelog : v0.32.3...v0.32.4 Assets 19 Loading Uh oh!
- There was an error while loading.
Entities in this story
Related events