提交历史

作者 SHA1 备注 提交日期
  royjhan a5f23d766e Merge branch 'main' into royh-batchembed 10 月之前
  Roy Han 00a4cb26ca use float32 10 月之前
  Josh Yan 33a65e3ba3 error 10 月之前
  Roy Han aee25acb5b move normalization to go 10 月之前
  Daniel Hiltgen 3518aaef33 Merge pull request #4218 from dhiltgen/auto_parallel 10 月之前
  Roy Han c111d8bb51 normalization 10 月之前
  Roy Han 49e341147d add server function 10 月之前
  Roy Han c406fa7a4c api/embed draft 10 月之前
  Roy Han ff191d7cba Initial Draft 10 月之前
  Blake Mizerany cb42e607c5 llm: speed up gguf decoding by a lot (#5246) 10 月之前
  Roy Han 0f87628b6d Revert "Initial Batch Embedding" 10 月之前
  Daniel Hiltgen 17b7186cd7 Enable concurrency by default 1 年之前
  Daniel Hiltgen 5bf5aeec01 Refine mmap default logic on linux 10 月之前
  Daniel Hiltgen 96624aa412 Merge pull request #5072 from dhiltgen/windows_path 10 月之前
  Roy Han c22d54895a Initial Batch Embedding 10 月之前
  Daniel Hiltgen 7784ca33ce Tighten up memory prediction logging 10 月之前
  Daniel Hiltgen 171796791f Adjust mmap logic for cuda windows for faster model load 10 月之前
  Daniel Hiltgen b2799f111b Move libraries out of users path 10 月之前
  Daniel Hiltgen da3bf23354 Workaround gfx900 SDMA bugs 11 月之前
  Daniel Hiltgen 6f351bf586 review comments and coverage 11 月之前
  Daniel Hiltgen fc37c192ae Refine CPU load behavior with system memory visibility 11 月之前
  Daniel Hiltgen 6fd04ca922 Improve multi-gpu handling at the limit 11 月之前
  Craig Hughes b84aea1685 Critical fix from llama.cpp JSON grammar to forbid un-escaped escape characters inside strings, which breaks parsing. (#3782) 11 月之前
  Michael Yang e40145a39d lint 11 月之前
  Michael Yang c895a7d13f some gocritic 11 月之前
  Michael Yang 829ff87bd1 revert tokenize ffi (#4761) 11 月之前
  Jeffrey Morgan a50a87a7b8 partial offloading: allow flash attention and disable mmap (#4734) 11 月之前
  Michael Yang 26a00a0410 use ffi for tokenizing/detokenizing 1 年之前
  Daniel Hiltgen 92c81e8117 Give the final model loading more time 11 月之前
  Lei Jitang 7487229c34 llm/server.go: Fix 2 minor typos (#4661) 11 月之前