[Prototype] Create and use custom NCCL group for aDAG #7568

ruisearch42 · 2024-08-15T21:50:51Z

FILL IN THE PR DESCRIPTION HERE

FIX #xxxx (link existing issues this PR will resolve)

BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE

PR Checklist (Click to Expand)

Thank you for your contribution to vLLM! Before submitting the pull request, please ensure the PR meets the following criteria. This helps vLLM maintain the code quality and improve the efficiency of the review process.

PR Title and Classification

Only specific types of PRs will be reviewed. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:

[Bugfix] for bug fixes.
[CI/Build] for build or continuous integration improvements.
[Doc] for documentation fixes and improvements.
[Model] for adding a new model or improving an existing model. Model name should appear in the title.
[Frontend] For changes on the vLLM frontend (e.g., OpenAI API server, LLM class, etc.)
[Kernel] for changes affecting CUDA kernels or other compute kernels.
[Core] for changes in the core vLLM logic (e.g., LLMEngine, AsyncLLMEngine, Scheduler, etc.)
[Hardware][Vendor] for hardware-specific changes. Vendor name should appear in the prefix (e.g., [Hardware][AMD]).
[Misc] for PRs that do not fit the above categories. Please use this sparingly.

Note: If the PR spans more than one category, please include all relevant prefixes.

Code Quality

The PR need to meet the following code quality standards:

We adhere to Google Python style guide and Google C++ style guide.
Pass all linter checks. Please use format.sh to format your code.
The code need to be well-documented to ensure future contributors can easily understand the code.
Include sufficient tests to ensure the project to stay correct and robust. This includes both unit tests and integration tests.
Please add documentation to docs/source/ if the PR modifies the user-facing behaviors of vLLM. It helps vLLM user understand and utilize the new features or changes.

Notes for Large Changes

Please keep the changes as concise as possible. For major architectural changes (>500 LOC excluding kernel/data/config/test), we would expect a GitHub issue (RFC) discussing the technical design and justification. Otherwise, we will tag it with rfc-required and might not go through the PR.

What to Expect for the Reviews

The goal of the vLLM team is to be a transparent reviewing machine. We would like to make the review process transparent and efficient and make sure no contributor feel confused or frustrated. However, the vLLM team is small, so we need to prioritize some PRs over others. Here is what you can expect from the review process:

After the PR is submitted, the PR will be assigned to a reviewer. Every reviewer will pick up the PRs based on their expertise and availability.
After the PR is assigned, the reviewer will provide status update every 2-3 days. If the PR is not reviewed within 7 days, please feel free to ping the reviewer or the vLLM team.
After the review, the reviewer will put an action-required label on the PR if there are changes required. The contributor should address the comments and ping the reviewer to re-review the PR.
Please respond to all comments within a reasonable time frame. If a comment isn't clear or you disagree with a suggestion, feel free to ask for clarification or discuss the suggestion.

Thank You

Finally, thank you for taking the time to read these guidelines and for your interest in contributing to vLLM. Your contributions make vLLM a great tool for everyone!

Signed-off-by: Rui Qiao <ruisearch42@gmail.com>

github-actions · 2024-08-15T21:51:06Z

👋 Hi! Thank you for contributing to the vLLM project.
Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which consists a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of default ones by unblocking the steps in your fast-check build on Buildkite UI.

Once the PR is approved and ready to go, please make sure to run full CI as it is required to merge (or just use auto-merge).

To run full CI, you can do one of these:

Comment /ready on the PR
Add ready label to the PR
Enable auto-merge.

🚀

rkooo567

this is not working e2e yet right?

rkooo567 · 2024-08-16T04:03:59Z

vllm/distributed/parallel_state.py

    if _WORLD is None:
        ranks = list(range(torch.distributed.get_world_size()))
        _WORLD = init_world_group(ranks, local_rank, backend)
+        _ADAG_WORLD = AdagNcclGroup(_WORLD, workers)


is this part necessary? is there any way to just pass existing group to .experimental_compile?

There needs to be some contract for the communicator used in aDAG. An interface would capture that contract. We directly pass in existing group, but it could fail at runtime if the contract is broken, which is less desired than enforcement at compile time.

rkooo567 · 2024-08-16T04:06:41Z

vllm/distributed/parallel_state.py

+        shape: Tuple[int],
+        dtype: "torch.dtype",
+        peer_rank: int,
+        allocator: Optional[TorchTensorAllocator] = None,


how does this allocator work? do we really need to make it a part of interface?

ruisearch42 · 2024-08-19T21:56:28Z

this is not working e2e yet right?

Not yet. Currently validating new API only.

Signed-off-by: Rui Qiao <ruisearch42@gmail.com>

Allow custom NCCL group for aDAG so that we can reuse what the user already created. Marking NcclGroupInterface as DeveloperAPI for now. After validation by using it in vLLM we can change to alpha stability. vLLM prototype: vllm-project/vllm#7568

Allow custom NCCL group for aDAG so that we can reuse what the user already created. Marking NcclGroupInterface as DeveloperAPI for now. After validation by using it in vLLM we can change to alpha stability. vLLM prototype: vllm-project/vllm#7568 Signed-off-by: ujjawal-khare <ujjawal.khare@dream11.com>

[Prototype] Create and use custom NCCL group for aDAG

6f683c0

Signed-off-by: Rui Qiao <ruisearch42@gmail.com>

ruisearch42 mentioned this pull request Aug 15, 2024

[aDAG] Allow custom NCCL group for aDAG ray-project/ray#47141

Merged

8 tasks

rkooo567 reviewed Aug 16, 2024

View reviewed changes

up

b42196e

Signed-off-by: Rui Qiao <ruisearch42@gmail.com>

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Prototype] Create and use custom NCCL group for aDAG #7568

[Prototype] Create and use custom NCCL group for aDAG #7568

ruisearch42 commented Aug 15, 2024

github-actions bot commented Aug 15, 2024

rkooo567 left a comment

rkooo567 Aug 16, 2024

ruisearch42 Aug 19, 2024

rkooo567 Aug 16, 2024

ruisearch42 commented Aug 19, 2024 •

edited

Loading

[Prototype] Create and use custom NCCL group for aDAG #7568

Are you sure you want to change the base?

[Prototype] Create and use custom NCCL group for aDAG #7568

Conversation

ruisearch42 commented Aug 15, 2024

PR Title and Classification

Code Quality

Notes for Large Changes

What to Expect for the Reviews

Thank You

github-actions bot commented Aug 15, 2024

rkooo567 left a comment

Choose a reason for hiding this comment

rkooo567 Aug 16, 2024

Choose a reason for hiding this comment

ruisearch42 Aug 19, 2024

Choose a reason for hiding this comment

rkooo567 Aug 16, 2024

Choose a reason for hiding this comment

ruisearch42 commented Aug 19, 2024 • edited Loading

ruisearch42 commented Aug 19, 2024 •

edited

Loading