Skip to content

[train][tests] Fix hanging test test_abort_generation_vllm_engine #1202

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.

Sign up for GitHub

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

Merged
CharlieFRuan merged 3 commits into from
Feb 24, 2026
Merged

[train][tests] Fix hanging test test_abort_generation_vllm_engine #1202

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d0923c0
remove older abort generation test
SumanthRH Feb 24, 2026
1ef235f
fix failing test
SumanthRH Feb 24, 2026
a9e20b4
x
SumanthRH Feb 24, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions skyrl-train/tests/gpu/gpu_ci/test_pause_and_continue_generation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -331,7 +331,7 @@ async def one_req(i: int):
"messages": convs[i],
**sampling_params,
}
return await client.chat_completion({"json": body, "headers": {}})
return await client.engines[0].chat_completion({"json": body, "headers": {}})
else:
# completions: prompt is a string
prompt_str = tokenizer.apply_chat_template(convs[i], add_generation_prompt=True, tokenize=False)
Expand All @@ -340,7 +340,7 @@ async def one_req(i: int):
"prompt": prompt_str,
**sampling_params,
}
return await client.completion({"json": body, "headers": {}})
return await client.engines[0].completion({"json": body, "headers": {}})

tasks = [asyncio.create_task(one_req(i)) for i in range(4)]
# Wait to let it run a bit, then pause generation
Expand Down
4 changes: 2 additions & 2 deletions tests/backends/skyrl_train/gpu/gpu_ci/test_pause_and_continue_generation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -331,7 +331,7 @@ async def one_req(i: int):
"messages": convs[i],
**sampling_params,
}
return await client.chat_completion({"json": body, "headers": {}})
return await client.engines[0].chat_completion({"json": body, "headers": {}})
else:
# completions: prompt is a string
prompt_str = tokenizer.apply_chat_template(convs[i], add_generation_prompt=True, tokenize=False)
Expand All @@ -340,7 +340,7 @@ async def one_req(i: int):
"prompt": prompt_str,
**sampling_params,
}
return await client.completion({"json": body, "headers": {}})
return await client.engines[0].completion({"json": body, "headers": {}})

tasks = [asyncio.create_task(one_req(i)) for i in range(4)]
# Wait to let it run a bit, then pause generation
Expand Down
Loading