Skip to content

fix: Dockerfile.sglang-deepep, sglang 0.4.7 compatible with sgl-kernel <= 0.1.8 #1595

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

Jump to bottom
Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: Dockerfile.sglang-deepep, sglang 0.4.7 compatible with sgl-kernel <= 0.1.8 #1595

wants to merge 1 commit into from
+1 −1

Conversation

ZacWang
Copy link

@ZacWang ZacWang commented Jun 19, 2025 •
edited by coderabbitai bot
Loading

Overview:

fix dockerfile for sglang deepep, should use sgl-kernel <=0.1.8 for sglang 0.4.7

Details:

when using current sglang main branch to build base image, it will install sgl-kernel==0.1.9.
this will cause the following error when launch decode nodes:

2025-06-19T08:18:45.701Z ERROR scheduler.run_scheduler_process: Scheduler hit an exception: Traceback (most recent call last):
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/managers/scheduler.py", line 2490, in run_scheduler_process
    scheduler = Scheduler(server_args, port_args, gpu_id, tp_rank, pp_rank, dp_rank)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/managers/scheduler.py", line 282, in __init__
    self.tp_worker = TpWorkerClass(
                     ^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/managers/tp_worker_overlap_thread.py", line 64, in __init__
    self.worker = TpModelWorker(
                  ^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/managers/tp_worker.py", line 78, in __init__
    self.model_runner = ModelRunner(
                        ^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/model_executor/model_runner.py", line 212, in __init__
    self.initialize(min_per_gpu_memory)
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/model_executor/model_runner.py", line 287, in initialize
    self.init_cuda_graphs()
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/model_executor/model_runner.py", line 1138, in init_cuda_graphs
    self.cuda_graph_runner = CudaGraphRunner(self)
                             ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/model_executor/cuda_graph_runner.py", line 305, in __init__
    self.capture()
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/model_executor/cuda_graph_runner.py", line 374, in capture
    ) = self.capture_one_batch_size(bs, forward)
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-pa
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1762, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/models/deepseek_v2.py", line 1485, in forward
    hidden_states = self.self_attn(
                    ^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1762, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/models/deepseek_v2.py", line 822, in forward
    s = self.forward_prepare(
        ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/models/deepseek_v2.py", line 857, in forward_prepare
    inner_state = self.forward_absorb_prepare(
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/models/deepseek_v2.py", line 946, in forward_absorb_prepare
    q, latent_cache = self.fused_qkv_a_proj_with_mqa(hidden_states)[0].split(
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1762, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/layers/linear.py", line 288, in forward
    output = self.quant_method.apply(self, x, bias)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/layers/quantization/fp8.py", line 422, in apply
    return self.w8a8_block_fp8_linear(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/layers/quantization/fp8_utils.py", line 236, in deepgemm_w8a8_block_fp8_linear_with_fallback
    q_input, x_scale = sglang_per_token_group_quant_fp8(
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/sglang/srt/layers/quantization/fp8_kernel.py", line 312, in sglang_per_token_group_quant_fp8
    sgl_per_token_group_quant_fp8(x, x_q, x_s, group_size, eps, fp8_min, fp8_max)
TypeError: sgl_per_token_group_quant_fp8() missing 1 required positional argument: 'scale_ue8m0'

Where should the reviewer start?

container/Dockerfile.sglang-deepep

Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)

Summary by CodeRabbit

  • Chores
    • Updated environment to include the "sgl-kernel" package version 0.1.8 during installation.

@ZacWang
Update Dockerfile.sglang-deepep, sglang 0.4.7 is compatible with sgl-…
9b9927c 
…kernel<=0.1.8

Signed-off-by: Zac <ZacWang@users.noreply.github.com>
@copy-pr-bot copy-pr-bot
Copy link

copy-pr-bot bot commented Jun 19, 2025

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@github-actions github-actions bot added the fix label Jun 19, 2025
@github-actions GitHub Actions
Copy link

👋 Hi ZacWang! Thank you for contributing to ai-dynamo/dynamo.

Just a reminder: The NVIDIA Test Github Validation CI runs an essential subset of the testing framework to quickly catch errors.Your PR reviewers may elect to test the changes comprehensively before approving your changes.

🚀

@github-actions github-actions bot added the external-contribution Pull request is from an external contributor label Jun 19, 2025
@coderabbitai coderabbitai
Copy link
Contributor

coderabbitai bot commented Jun 19, 2025

Walkthrough

The Dockerfile for the sglang-deepep container has been updated to install the "sgl-kernel" Python package version 0.1.8 in addition to "sglang" version 0.4.7, following the removal of any pre-existing "sglang" installation. No other logic or control flow changes are present.

Changes

File(s) Change Summary
container/Dockerfile.sglang-deepep Add installation of "sgl-kernel==0.1.8" alongside "sglang==0.4.7".

Poem

In Docker’s gentle, cozy keep,
New kernels join while old ones sleep.
Sglang and friends, now side by side,
In versioned harmony they reside.
With every build, we leap ahead—
🐇 Hopping forward, well-fed!

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Explain this complex logic.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai explain this code block.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

coderabbitai[bot]
coderabbitai bot reviewed Jun 19, 2025
View reviewed changes
Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 0

🧹 Nitpick comments (1)
container/Dockerfile.sglang-deepep (1)

48-48: Pin sgl-kernel to 0.1.8 to maintain compatibility
Constraining sgl-kernel==0.1.8 alongside sglang==0.4.7 prevents the runtime TypeError caused by the missing scale_ue8m0 argument in v0.1.9.

Consider merging the uninstall (pip uninstall), removal (rm -rf sglang), and install (pip install …) into a single RUN directive and adding --no-cache-dir to pip installs to streamline layers and reduce image size.

📜 Review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between dd3c470 and 9b9927c.

📒 Files selected for processing (1)
  • container/Dockerfile.sglang-deepep (1 hunks)
⏰ Context from checks skipped due to timeout of 90000ms (2)
  • GitHub Check: Build and Test - vllm
  • GitHub Check: pre-commit

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@coderabbitai coderabbitai[bot] coderabbitai[bot] left review comments

@rmccorm4 rmccorm4 Awaiting requested review from rmccorm4 rmccorm4 is a code owner

@tanmayv25 tanmayv25 Awaiting requested review from tanmayv25 tanmayv25 is a code owner

@richardhuo-nv richardhuo-nv Awaiting requested review from richardhuo-nv richardhuo-nv is a code owner

@ptarasiewiczNV ptarasiewiczNV Awaiting requested review from ptarasiewiczNV ptarasiewiczNV is a code owner

@ishandhanani ishandhanani Awaiting requested review from ishandhanani ishandhanani is a code owner

@alec-flowers alec-flowers Awaiting requested review from alec-flowers alec-flowers is a code owner

@nnshah1 nnshah1 Awaiting requested review from nnshah1 nnshah1 is a code owner

At least 1 approving review is required to merge this pull request.

Assignees
No one assigned
Labels
external-contribution Pull request is from an external contributor fix size/XS
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@ZacWang