test_fused_moe_blockwise.py 改了一下shape，单测过不了
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 1.2k
- Forks
- 142
- Avg merge
- 23h 15m
- Merged PRs (30d)
- 8
Description
@pytest.mark.parametrize("num_tokens", [128])
@pytest.mark.parametrize("num_topk", [8])
@pytest.mark.parametrize("hidden_size", [4096])
@pytest.mark.parametrize("intermediate_size", [1536])
@pytest.mark.parametrize("num_expert", [128])
@pytest.mark.parametrize("rank_ep", [0, 1, 2, 3, 4, 5, 6, 7])
@pytest.mark.parametrize("size_ep", [8])
@pytest.mark.parametrize("has_shared_output", [False, True])
FAILED test_fuse_moe_blockwise.py::test_fuse_moe_blockwise_fp8[False-8-0-128-1536-4096-8-128] - AssertionError: assert False
FAILED test_fuse_moe_blockwise.py::test_fuse_moe_blockwise_fp8[True-8-1-128-1536-4096-8-128] - AssertionError: assert False
FAILED test_fuse_moe_blockwise.py::test_fuse_moe_blockwise_fp8[True-8-5-128-1536-4096-8-128] - AssertionError: assert False
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with test_fuse_moe_blockwise.py and rerun the failing test_fuse_moe_blockwise_fp8 parametrizations shown in the report. Compare the changed shape parameters with the failures and use the existing assertions to identify the expected behavior; done means all listed parametrizations pass.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, python
- Domain
- machine-learning, testing-qa
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 55/100