AI Stack

TAGS / TERM

模型部署

共 187 篇

  1. Ggml.ai 加入 Hugging Face 推动本地 AI 长期发展 2026-02-21 · HACKER_NEWS
  2. GGML与llama.cpp加入HF以推动本地AI长期发展 2026-02-21 · BLOGS_PODCASTS
  3. Ggml.ai加入Hugging Face推动本地AI长期发展 2026-02-21 · HACKER_NEWS
  4. GGML与llama.cpp加入HF以保障本地AI长期发展 2026-02-20 · BLOGS_PODCASTS
  5. Ggml.ai加入Hugging Face以推动本地AI长期发展 2026-02-20 · HACKER_NEWS
  6. 2025年回顾：SageMaker AI弹性训练计划与推理性价比优化 2026-02-20 · BLOGS_PODCASTS
  7. GGML与llama.cpp加入HF推动本地AI长期发展 2026-02-20 · BLOGS_PODCASTS
  8. Ggml.ai加入Hugging Face以推动本地AI长期发展 2026-02-20 · HACKER_NEWS
  9. 通往泛在AI之路：实现每秒1.7万tokens推理 2026-02-20 · HACKER_NEWS
  10. 通往无处不在的AI：实现每秒1.7万tokens推理 2026-02-20 · HACKER_NEWS
  11. Ggml.ai 加入 Hugging Face 推动本地 AI 长期发展 2026-02-20 · HACKER_NEWS
  12. Step 3.5 Flash 开源基础模型：支持高速深度推理 2026-02-19 · HACKER_NEWS
  13. Step 3.5 Flash：快到能思考，稳到可执行 2026-02-19 · HACKER_NEWS
  14. Codex与Claude支持定制内核以适配各类应用 2026-02-14 · BLOGS_PODCASTS
  15. NVIDIA Nemotron 3 Nano 30B 模型现已在 Amazon SageMaker JumpS 2026-02-13 · BLOGS_PODCASTS
  16. 仅更换框架，一下午提升15个大模型代码能力 2026-02-13 · HACKER_NEWS
  17. NVIDIA Nemotron 3 Nano 30B 现已登陆 Amazon SageMaker JumpSt 2026-02-13 · BLOGS_PODCASTS
  18. NVIDIA Nemotron 3 Nano 30B 现已登陆 Amazon SageMaker JumpSt 2026-02-12 · BLOGS_PODCASTS
  19. NVIDIA Nemotron 3 Nano 30B 现已在 Amazon SageMaker JumpSta 2026-02-12 · BLOGS_PODCASTS
  20. NVIDIA Nemotron 3 Nano 30B 现已在 Amazon SageMaker JumpSta 2026-02-12 · BLOGS_PODCASTS
  21. NVIDIA Nemotron 3 Nano 30B 现已在 Amazon SageMaker JumpSta 2026-02-12 · BLOGS_PODCASTS
  22. NVIDIA Nemotron 3 Nano 30B 现已登陆 Amazon SageMaker JumpSt 2026-02-12 · BLOGS_PODCASTS
  23. NVIDIA Nemotron 3 Nano 30B 现已登陆 Amazon SageMaker JumpSt 2026-02-12 · BLOGS_PODCASTS
  24. NVIDIA Nemotron 3 Nano 30B 模型现已在 Amazon SageMaker JumpS 2026-02-12 · BLOGS_PODCASTS
  25. NVIDIA Nemotron 3 Nano 30B 现已登陆 Amazon SageMaker JumpSt 2026-02-12 · BLOGS_PODCASTS
  26. LoRA-Squeeze：LoRA模块的调优后与调优中压缩方法 2026-02-12 · ARXIV
  27. Agent-to-agent collaboration: Using Amazon Nova 2 Lite 2026-02-11 · BLOGS_PODCASTS
  28. 利用 Hugging Face 与 SageMaker 扩展企业级 LLM 微调 2026-02-10 · BLOGS_PODCASTS
  29. Pure C, CPU-only inference with Mistral Voxtral Realtim 2026-02-10 · HACKER_NEWS
  30. Pure C, CPU-only inference with Mistral Voxtral Realtim 2026-02-10 · HACKER_NEWS
  31. 纯C语言实现Mistral Voxtral 4B语音模型CPU推理 2026-02-10 · HACKER_NEWS
  32. 全球开源AI生态展望：从DeepSeek到AI+ 2026-02-05 · BLOGS_PODCASTS
  33. 全球开源AI生态展望：从DeepSeek到AI+ 2026-02-04 · BLOGS_PODCASTS
  34. iPhone 16 Pro Max 运行 MLX 大模型输出质量差 2026-02-02 · HACKER_NEWS
  35. iPhone 16 Pro Max 运行 MLX 大模型输出异常 2026-02-02 · HACKER_NEWS
  36. 中国开源AI生态的架构选择：超越DeepSeek的构建路径 2026-01-29 · BLOGS_PODCASTS
  37. 谷歌将 Gemini 模型集成至 Chrome 浏览器 2026-01-29 · HACKER_NEWS