Issue Station
Sign In
Tools hereToolbox

vllm - 💡(How to fix) Fix [Bug]: disaggregated_prefill.py example broken - P2pNcclConnector incompatible with offline mode

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

Root Cause

Root cause: P2pNcclConnector.parse_request_id() expects request_id to contain ___decode_addr_IP:PORT or ___prefill_addr_IP:PORT___ patterns, which are injected by a proxy in online serving mode. In offline mode there is no proxy, so this information is never present in the request_id.

Fix Action

Fix / Workaround

Note: VLLM_DISABLE_REQUEST_ID_RANDOMIZATION=1 workaround does not help.

RAW_BUFFERClick to expand / collapse

Your current environment

Environment:

  • vLLM version: 0.22.0
  • Hardware: 2x NVIDIA L40 46GB
  • OS: Ubuntu, CUDA 13.0
  • Model: Qwen/Qwen3-8B

🐛 Describe the bug

Environment:

  • vLLM version: 0.22.0
  • Hardware: 2x NVIDIA L40 46GB
  • OS: Ubuntu, CUDA 13.0
  • Model: Qwen/Qwen3-8B

Description: Running examples/disaggregated/disaggregated_prefill.py with P2pNcclConnector fails with:

ValueError: Request id 0 does not contain hostname and port

Root cause: P2pNcclConnector.parse_request_id() expects request_id to contain ___decode_addr_IP:PORT or ___prefill_addr_IP:PORT___ patterns, which are injected by a proxy in online serving mode. In offline mode there is no proxy, so this information is never present in the request_id.

The example script implies P2pNcclConnector works in offline mode, but it is fundamentally designed for proxy-based online serving only. The example is misleading or broken.

Note: VLLM_DISABLE_REQUEST_ID_RANDOMIZATION=1 workaround does not help.

Steps to reproduce:

  1. Run python examples/disaggregated/disaggregated_prefill.py
  2. After fixing the port conflict issue (bug #1), script fails with ValueError on request_id

Related: #38808

disaggregated_prefill_error.log

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

vllm - 💡(How to fix) Fix [Bug]: disaggregated_prefill.py example broken - P2pNcclConnector incompatible with offline mode