Mike Iovine
Mike Iovine
This looks like a known issue with graph mode that should be fixed in the next release. For now I recommend setting `graph_mode=False` to test this case.
Hey @wanghuihhh, so I thought this was a separate issue, but it looks like something else entirely. The problem is that we were starting our stream captures with `cudaStreamCaptureModeGlobal` instead...
The real root cause is that it can't find the compiled model: ``` OSError: ./tmp/CLIPTextModel/test.so: cannot open shared object file: No such file or directory ``` This likely indicates that...
Looks like something in cutlass is failing to compile, can you share your compiler version, cutlass version, CUDA version, etc?
/bot run --disable-fail-fast
Sorry for the delay! I've missed this in the move to Github. Looks good to me assuming there are only trivial changes compared to what I reviewed internally.
/bot run --disable-fail-fast
/bot run --disable-fail-fast