Ollama v0.40.13扩展LFM3支持并修复Metal崩溃
AI 总结
Ollama v0.40.13让Liquid AI的LFM3模型（包括lfm3-audio和lfm3-omni）除支持Apple silicon外，也可运行于Linux和Windows。该版本还包含LFM3 GGUF修复、llama-server语音改动，并将llama.cpp升级至b11963。v0.40.13-rc1标签还加入了针对旧版macOS上Metal unary库崩溃回归问题的临时规避方案。
深度见解
此次更新扩大了LFM3本地部署的桌面平台范围，并处理了旧版macOS用户报告的Metal崩溃问题。
v0.40.13-rc1
- v0.40.13-rc1
-
04088e7 - Verified This commit was created on GitHub.com and signed with GitHub’s verified signature. GPG key ID: B5690EEEBB952194 Verified Learn about vigilant mode
- Choose a tag to compare Sorry, something went wrong. Filter Loading Sorry, something went wrong. Uh oh! There was an error while loading. Please reload this page. No results found View all tags
v0.40.13-rc1: llama.cpp: workaround Metal unary crash (#19372)
- v0.40.13-rc1
-
04088e7 - Choose a tag to compare Sorry, something went wrong. Filter Loading Sorry, something went wrong. Uh oh! There was an error while loading. Please reload this page. No results found View all tags
- Verified This commit was created on GitHub.com and signed with GitHub’s verified signature. GPG key ID: B5690EEEBB952194 Verified Learn about vigilant mode
dhiltgen tagged this 28 Oct 22:20
#Ollama#Liquid AI#LFM3#lfm3-audio#lfm3-omni#llama.cpp#llama-server