Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Llama 3.1 8B F16 Non-Decomposed prefill fails to compile #3884

Open
aviator19941 opened this issue Nov 19, 2024 · 0 comments
Open

Llama 3.1 8B F16 Non-Decomposed prefill fails to compile #3884

aviator19941 opened this issue Nov 19, 2024 · 0 comments

Comments

@aviator19941
Copy link
Collaborator

Llama 3.1 8B F16 Non-Decomposed prefill fails to compile, but it was able to compile last week. It seems like the IR changed quite a bit, so I'm not sure if that has something to do with it.

IR from last week (COMPILES): https://gist.github.com/aviator19941/3443ef2f383a18f11659f979879ac4d7

IR from yesterday (FAILS): https://gist.github.com/aviator19941/e67f9c479400654596571cd50d905fda

compile command:
iree-compile f16_torch_prefill.mlir --iree-hip-target=gfx942 --iree-hal-target-backends=rocm -o=f16_torch_prefill.vmfb --iree-hal-dump-executable-files-to=files --iree-dispatch-creation-enable-aggressive-fusion=true --iree-global-opt-propagate-transposes=true --iree-opt-aggressively-propagate-transposes=true --iree-opt-data-tiling=false --iree-preprocessing-pass-pipeline='builtin.module(util.func(iree-preprocessing-generalize-linalg-matmul-experimental))' --iree-hal-force-indirect-command-buffers=true --iree-stream-resource-memory-model=discrete --iree-hip-legacy-sync=false

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant