deepseek-ai / deepseek-ai/DeepEP
[bug]Assert error run test_internode.py on EP128
- Dominant language
- Cuda
- Stars
- 10.1k
- Forks
- 1.4k
- Avg merge
- 2d 17h
- Merged PRs (30d)
- 3
Description
when run normal kernel use EP128, this assert will fail
```
Assertion error num_max_nvl_chunked_recv_tokens / num_rdma_ranks > std::max(num_max_rdma_chunked_send_tokens, num_max_nvl_chunked_send_tokens)'
```
because the `num_max_nvl_chunked_send_tokens` will be set to bigger than `num_max_nvl_chunked_recv_tokens / num_rdma_ranks` when tuning
```
for nvl_chunk_size in range(4, *45*, 4): // test_internode.py
```
it seems should add nvl_buffer_size to fix it
```
rdma_buffer_size, nvl_buffer_size = 128, (720 if num_ranks in (24, 48, 96, 144, 160) else 512)
-> rdma_buffer_size, nvl_buffer_size = 128, (720 if num_ranks in (24, 48, 96, 128,144, 160) else 512)
```
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with test_internode.py and locate the nvl_buffer_size selection and the nvl_chunk_size tuning loop. Run the normal-kernel EP128 case to reproduce the assertion, then verify the buffer-size adjustment prevents the failure without breaking the other listed rank configurations.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- distributed-systems
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 62/100