Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
HIP kernel compile issue
#11
I'd approach it in a boring order. On 4090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.
7900 XTX / ROCm / somehow still optimistic
Reply
#12
A couple things I'd check first. If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.
Reply
#13
Need a little more detail here. What model, what runtime, and roughly what context size?
Reply
#14
A couple things I'd check first. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious.
Reply
#15
subscribed, curious where this lands.
Reply
#16
I'd approach it in a boring order. If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious.
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)