提交历史

作者 SHA1 备注 提交日期
  Jesse Gross 854a9195f3 attention: Remove unnecessary contiguous operations 2 月之前
  Michael Yang 3e8b8a1933 ml: update Context.Forward interface 2 月之前
  Michael Yang 53d2990d9b model: add bos token if configured 2 月之前
  Jesse Gross f53f4198c3 ml: Abstract attention out of model definitions 2 月之前
  Jesse Gross bd6a7d5e64 ollamarunner: Pass runner performance parameters to backends 2 月之前
  Daniel Hiltgen df2680b4b9 Wire up system info log for new engine (#9123) 2 月之前
  Jesse Gross ed443a0393 Runner for Ollama engine 4 月之前
  Jesse Gross d773b7d671 backend: API to support full precision matmul 2 月之前
  Jesse Gross 4d4463b2bd backend: Support graph computation that does not return an output 2 月之前
  Jesse Gross 0e38297f87 backend: Consistently use int (vs. int64) for tensor shapes 2 月之前
  Jesse Gross 7e13f568dc backend: Don't return an error on Close 2 月之前
  Michael Yang 58245413f4 next ollama runner (#7913) 2 月之前