[PR #354] [CLOSED] fix #532

New issue

Closed

opened 2026-10-27 21:03:44 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-27 21:03:44 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepEP/pull/354
Author: @alpha-baby
Created: 8/7/2025
Status: ❌ Closed

Base: main ← Head: fujh/fix_test_low_latency

📝 Commits (1)

2c67959 fix

📊 Changes

1 file changed (+8 additions, -2 deletions)

View changed files

📝 tests/test_low_latency.py (+8 -2)

📄 Description

use my new test script

test command:

python3  ./tests/test_low_latency_bak.py --num-tokens 18 --hidden 7168 --num-topk 1 --num-experts 8

failed log:

Traceback (most recent call last):
  File "/home/root/qiongyu.zqy/fujianhao.fjh/origin-DeepEP/./tests/test_low_latency_bak.py", line 227, in <module>
    torch.multiprocessing.spawn(test_loop, args=(num_processes, args), nprocs=num_processes)
  File "/opt/conda/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 340, in spawn
    return start_processes(fn, args, nprocs, join, daemon, start_method="spawn")
  File "/opt/conda/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 296, in start_processes
    while not context.join():
  File "/opt/conda/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 215, in join
    raise ProcessRaisedException(msg, error_index, failed_process.pid)
torch.multiprocessing.spawn.ProcessRaisedException:

-- Process 5 terminated with the following error:
Traceback (most recent call last):
  File "/opt/conda/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 90, in _wrap
    fn(i, *args)
  File "/home/root/qiongyu.zqy/fujianhao.fjh/origin-DeepEP/tests/test_low_latency_bak.py", line 183, in test_loop
    test_main(num_tokens, hidden, num_experts, num_topk, rank, num_ranks, group, buffer,
  File "/home/root/qiongyu.zqy/fujianhao.fjh/origin-DeepEP/tests/test_low_latency_bak.py", line 100, in test_main
    assert (recv_x[begin_idx:begin_idx + count][:, -128:] - recv_src_info[begin_idx:begin_idx + count].reshape(count,1)).sum().item() == 0
AssertionError

use this command will be not failed

python3  ./tests/test_low_latency_bak.py --num-tokens 16 --hidden 7168 --num-topk 1 --num-experts 8

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/DeepEP/pull/354 **Author:** [@alpha-baby](https://github.com/alpha-baby) **Created:** 8/7/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `fujh/fix_test_low_latency` --- ### 📝 Commits (1) - [`2c67959`](https://github.com/deepseek-ai/DeepEP/commit/2c6795945f4c029b8ae1c1b34e4514c6a9bf4c89) fix ### 📊 Changes **1 file changed** (+8 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `tests/test_low_latency.py` (+8 -2) </details> ### 📄 Description use my new test script test command: ``` python3 ./tests/test_low_latency_bak.py --num-tokens 18 --hidden 7168 --num-topk 1 --num-experts 8 ``` failed log: ``` Traceback (most recent call last): File "/home/root/qiongyu.zqy/fujianhao.fjh/origin-DeepEP/./tests/test_low_latency_bak.py", line 227, in <module> torch.multiprocessing.spawn(test_loop, args=(num_processes, args), nprocs=num_processes) File "/opt/conda/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 340, in spawn return start_processes(fn, args, nprocs, join, daemon, start_method="spawn") File "/opt/conda/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 296, in start_processes while not context.join(): File "/opt/conda/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 215, in join raise ProcessRaisedException(msg, error_index, failed_process.pid) torch.multiprocessing.spawn.ProcessRaisedException: -- Process 5 terminated with the following error: Traceback (most recent call last): File "/opt/conda/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 90, in _wrap fn(i, *args) File "/home/root/qiongyu.zqy/fujianhao.fjh/origin-DeepEP/tests/test_low_latency_bak.py", line 183, in test_loop test_main(num_tokens, hidden, num_experts, num_topk, rank, num_ranks, group, buffer, File "/home/root/qiongyu.zqy/fujianhao.fjh/origin-DeepEP/tests/test_low_latency_bak.py", line 100, in test_main assert (recv_x[begin_idx:begin_idx + count][:, -128:] - recv_src_info[begin_idx:begin_idx + count].reshape(count,1)).sum().item() == 0 AssertionError ``` use this command will be not failed ``` python3 ./tests/test_low_latency_bak.py --num-tokens 16 --hidden 7168 --num-topk 1 --num-experts 8 ``` --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-27 21:03:44 +00:00