提交历史

作者 SHA1 备注 提交日期
  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 11 月之前
  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
  Daniel Hiltgen 0165ba1651 Merge pull request #4638 from dhiltgen/better_error 11 月之前
  Daniel Hiltgen c4209d6d21 Report better warning on client closed abort of load 11 月之前
  Patrick Devine 4cc3be3035 Move envconfig and consolidate env vars (#4608) 11 月之前
  Daniel Hiltgen b37b496a12 Wire up load progress 11 月之前
  Jeffrey Morgan 38255d2af1 Use flash attention flag for now (#4580) 11 月之前
  Sam e15307fdf4 feat: add support for flash_attn (#4120) 11 月之前
  Patrick Devine d1692fd3e0 fix the cpu estimatedTotal memory + get the expiry time for loading models (#4461) 11 月之前
  Daniel Hiltgen 853ae490e1 Sanitize the env var debug log 11 月之前
  Patrick Devine 6845988807 Ollama `ps` command for showing currently loaded models (#4327) 11 月之前
  jmorganca 92ca2cca95 Revert "only forward some env vars" 11 月之前
  Daniel Hiltgen c4014e73a2 Fall back to CPU runner with zero layers 11 月之前
  Jeffrey Morgan bb6fd02298 Don't clamp ctx size in `PredictServerFit` (#4317) 11 月之前
  Michael Yang cf442cd57e fix typo 11 月之前
  Michael Yang ce3b212d12 only forward some env vars 11 月之前
  Michael Yang 58876091f7 log clean up 11 月之前
  Daniel Hiltgen d0425f26cf Merge pull request #4294 from dhiltgen/harden_subprocess_reaping 11 月之前
  Bruce MacDonald cfa84b8470 add done_reason to the api (#4235) 11 月之前
  Daniel Hiltgen 84ac7ce139 Refine subprocess reaping 11 月之前
  Daniel Hiltgen 920a4b0794 Merge remote-tracking branch 'upstream/main' into pr3702 11 月之前
  Daniel Hiltgen ee49844d09 Merge pull request #4153 from dhiltgen/gpu_verbose_response 11 月之前
  Daniel Hiltgen bee2f4a3b0 Record GPU usage information 1 年之前
  Daniel Hiltgen 72700279e2 Detect noexec and report a better error 1 年之前
  Daniel Hiltgen 380378cc80 Use our libraries first 1 年之前