You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
File "/home/sai/actions-runner-llama/_work/SHARK-Platform/SHARK-Platform/deps/iree-turbine/iree/turbine/aot/params.py", line 234, in load
E self._index.load(
E ValueError: Error opening parameter file: c/runtime/src/iree/base/internal/file_io.c:253: NOT_FOUND; failed to open file '/data/llama-3.1/weights/405b/f8/llama405b_fp8.irpa'
E
E
E Invoked with:
E cd /home/sai/actions-runner-llama/_work/SHARK-Platform/SHARK-Platform && python3 -m sharktank.examples.export_paged_llm_v1 --irpa-file=/data/llama-3.1/weights/405b/f8/llama405b_fp8.irpa --output-mlir=/home/sai/actions-runner-llama/_work/SHARK-Platform/SHARK-Platform/2024-11-10/llama-405b/fp8_decomposed.mlir --output-config=/home/sai/actions-runner-llama/_work/SHARK-Platform/SHARK-Platform/2024-11-10/llama-405b/fp8_decomposed.json --bs=4 --attention-kernel decomposed
The text was updated successfully, but these errors were encountered:
Those tests should still be changed to not depend on the contents of the runner file system. Users and developers should be able to run these tests on their own systems.
Have the test declare what files it needs, and check during setup if those files exist
Use environment variables for cache locations (e.g. HF_HOME, or SHARK_HOME), not hardcoded paths (and especially not hardcoded paths that won't work at all on Windows)
If the files do not exist, fail the test and print instructions for downloading the files (e.g. print a script/command to run)
If the downloads are small enough, the test could download and cache automatically. For larger models, I'd probably fail the test (or skip with a reason) and print instructions to run some setup.
@ScottTodd I agree. However, as someone who is grateful these tests were written at all, I went ahead and updated the fs for now. we can leave this issue open if you'd like to use it to track the desired modality
SGTM. I'll keep speaking up whenever it breaks and needs fixing though :P. We'll need the tests decoupled from the machines our team directly controls eventually if we want users or other developers to be able to run them too. (Though for 405b that's much harder than it is for smaller models)
In nightly, we have different decomposed models like
which are failing as parameter files are missing.
Error:
The text was updated successfully, but these errors were encountered: