trunk/7de327d9302fff6dc5b4271e04a7b5edadf12e33: flex_gemm: trim per-call CPU overhead in the QuACK launch path (#200712)
- PyTorch 近 90 天出现 2303 次
- PyTorch 近 90 天第 2273 次发版
- 上一次：同一天稍早 · trunk/10dc63912abee5b1c6b942e670872e515cbf9210: [CPP FakeTensor] Don't look up the op in register_fake (#200798)
发生了什么
Human Note Reduce FlexGEMM host overhead on the runtime launch path. Need for speed baby Agent note Every compiled FlexGEMM call entered torch.cuda.stream(torch.cuda.ExternalStream(stream)) and rebuilt the frozen GemmConfig from the codegen config tuple. Generated wrappers always pass the current raw stream, and QuACK's tvm-ffi launch already runs on torch's current stream, so the stream switch did nothing but cost…
摘要按规则整理自下方来源原文