Skip to content

[llm] Update vllm to 0.11.0 and Nixl to 0.6.0#57201

Merged
kouroshHakha merged 9 commits intoray-project:masterfrom
kouroshHakha:kh/update-vllm-0.11.0
Oct 8, 2025
Merged

[llm] Update vllm to 0.11.0 and Nixl to 0.6.0#57201
kouroshHakha merged 9 commits intoray-project:masterfrom
kouroshHakha:kh/update-vllm-0.11.0

Conversation

@kouroshHakha
Copy link
Copy Markdown
Contributor

Updating vLLM and Nixl -- notable changes:

  • Remove V0 from stack
  • Embedding is added to V1. So it should be ok

Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
@kouroshHakha kouroshHakha added the go add ONLY when ready to merge, run all tests label Oct 6, 2025
kouroshHakha and others added 3 commits October 5, 2025 17:45
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: Nikhil Ghosh <nikhil@anyscale.com>
@nrghosh nrghosh force-pushed the kh/update-vllm-0.11.0 branch from 2309954 to 2c00977 Compare October 7, 2025 01:52
Comment on lines +222 to +226
# runtime_env=dict(
# env_vars=dict(
# VLLM_USE_V1="0",
# ),
# ),
Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

if this passes the tests we should remove it.

Copy link
Copy Markdown
Contributor

@nrghosh nrghosh left a comment

Choose a reason for hiding this comment

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

  • unit tests fixed

  • release tests (probes/test_basic.py::test_logprobs)
    logprobs problem: -1 is being interpreted as a vocab size instead of an invalid # for logprobs so all release tests are barfing b/c that probe test fails.

  • release tests 1p1d / 2p6d faliing due to nixl error

TypeError: nixl_agent_config.__init__() got an unexpected keyword argument 'num_threads'

num_threads was added to nixl_agent_config between release/0.4.1 and release/0.6.0 at 9f77cc4

Issue: release env is still using nixl=0.4.1 which is causing the break
image

New issue - nixl linker / backend error

failed to load plugin from /usr/local/nixl/lib/x86_64-linux-gnu/plugins/libplugin_UCX_MO.so: /usr/local/nixl/lib/x86_64-linux-gnu/plugins/libplugin_UCX_MO.so: undefined symbol: _ZN12nixlDescListI12nixlMetaDescEC1ERK10nixl_mem_tRKbRKi

(RayWorkerWrapper pid=128409) INFO 10-07 11:58:24 [factory.py:51] Creating v1 connector with name: NixlConnector and engine_id: 16561289-139e-44af-90e7-1c86a61925b2-10.0.111.115-40773
(RayWorkerWrapper pid=128409) INFO 10-07 11:58:24 [nixl_connector.py:465] Initializing NIXL wrapper
(RayWorkerWrapper pid=128409) INFO 10-07 11:58:24 [nixl_connector.py:466] Initializing NIXL worker 16561289-139e-44af-90e7-1c86a61925b2-10.0.111.115-40773
(RayWorkerWrapper pid=128409) E1007 11:58:24.959858  128409 nixl_plugin_manager.cpp:122] Failed to load plugin from /usr/local/nixl/lib/x86_64-linux-gnu/plugins/libplugin_UCX_MO.so: /usr/local/nixl/lib/x86_64-linux-gnu/plugins/libplugin_UCX_MO.so: undefined symbol: _ZN12nixlDescListI12nixlMetaDescEC1ERK10nixl_mem_tRKbRKi
(RayWorkerWrapper pid=128409) E1007 11:58:24.959885  128409 nixl_plugin_manager.cpp:288] Failed to load plugin 'UCX_MO' from any directory

Resolved by reinstalling nixl (local issue)

- vllm-project/vllm#23868
- PR in vLLM changed interpretation of num_logprobs = -1
- Overrides to model_config.get_vocab_size(), which triggers
  openai.APIError instead of openai.badRequestError
- Test expects the latter, which causes failure
- Instead of broadening / changing the expected failure type, we use -2

Signed-off-by: Nikhil Ghosh <nikhil@anyscale.com>
@nrghosh nrghosh force-pushed the kh/update-vllm-0.11.0 branch from 4717751 to e62627f Compare October 7, 2025 05:23
@eicherseiji eicherseiji mentioned this pull request Oct 7, 2025
8 tasks
Signed-off-by: Nikhil Ghosh <nikhil@anyscale.com>
Signed-off-by: nikhil <nikhil@anyscale.com>
@nrghosh nrghosh force-pushed the kh/update-vllm-0.11.0 branch from 35427b5 to 8e6b2ab Compare October 7, 2025 21:02
@nrghosh nrghosh marked this pull request as ready for review October 7, 2025 21:04
@nrghosh nrghosh requested review from a team, aslonnie, edoakes and richardliaw as code owners October 7, 2025 21:04
Copy link
Copy Markdown
Collaborator

@aslonnie aslonnie left a comment

Choose a reason for hiding this comment

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

can we wait till 2.50 branch cut to merge this?

@kouroshHakha
Copy link
Copy Markdown
Contributor Author

@aslonnie ideally we can land this for summit?

@nrghosh
Copy link
Copy Markdown
Contributor

nrghosh commented Oct 7, 2025

can we wait till 2.50 branch cut to merge this?

I think we want to get this in ASAP, it has a lot of performance improvements

@eicherseiji
Copy link
Copy Markdown
Contributor

eicherseiji commented Oct 7, 2025

can we wait till 2.50 branch cut to merge this?

If we ship the switch to OpenTelemetry without vLLM 0.11.0 we will have no vLLM metrics in Ray 2.50. cc: @can-anyscale

Copy link
Copy Markdown
Contributor

@nrghosh nrghosh left a comment

Choose a reason for hiding this comment

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

Unit tests and release tests both passing

Doc build failure seems ephemeral / unrelated, as full doc build succeeds locally with this branch.

@kouroshHakha kouroshHakha enabled auto-merge (squash) October 8, 2025 01:01
@aslonnie aslonnie self-requested a review October 8, 2025 01:07
@ray-gardener ray-gardener bot added the serve Ray Serve Related Issue label Oct 8, 2025
@ray-gardener ray-gardener bot added the llm label Oct 8, 2025
@kouroshHakha kouroshHakha merged commit 32e59c2 into ray-project:master Oct 8, 2025
6 of 7 checks passed
liulehui pushed a commit to liulehui/ray that referenced this pull request Oct 9, 2025
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: Nikhil Ghosh <nikhil@anyscale.com>
Signed-off-by: nikhil <nikhil@anyscale.com>
Co-authored-by: Nikhil Ghosh <nikhil@anyscale.com>
Co-authored-by: Nikhil G <nrghosh@users.noreply.github.com>
joshkodi pushed a commit to joshkodi/ray that referenced this pull request Oct 13, 2025
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: Nikhil Ghosh <nikhil@anyscale.com>
Signed-off-by: nikhil <nikhil@anyscale.com>
Co-authored-by: Nikhil Ghosh <nikhil@anyscale.com>
Co-authored-by: Nikhil G <nrghosh@users.noreply.github.com>
Signed-off-by: Josh Kodi <joshkodi@gmail.com>
ArturNiederfahrenhorst pushed a commit to ArturNiederfahrenhorst/ray that referenced this pull request Oct 13, 2025
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: Nikhil Ghosh <nikhil@anyscale.com>
Signed-off-by: nikhil <nikhil@anyscale.com>
Co-authored-by: Nikhil Ghosh <nikhil@anyscale.com>
Co-authored-by: Nikhil G <nrghosh@users.noreply.github.com>
justinyeh1995 pushed a commit to justinyeh1995/ray that referenced this pull request Oct 20, 2025
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: Nikhil Ghosh <nikhil@anyscale.com>
Signed-off-by: nikhil <nikhil@anyscale.com>
Co-authored-by: Nikhil Ghosh <nikhil@anyscale.com>
Co-authored-by: Nikhil G <nrghosh@users.noreply.github.com>
xinyuangui2 pushed a commit to xinyuangui2/ray that referenced this pull request Oct 22, 2025
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: Nikhil Ghosh <nikhil@anyscale.com>
Signed-off-by: nikhil <nikhil@anyscale.com>
Co-authored-by: Nikhil Ghosh <nikhil@anyscale.com>
Co-authored-by: Nikhil G <nrghosh@users.noreply.github.com>
Signed-off-by: xgui <xgui@anyscale.com>
elliot-barn pushed a commit that referenced this pull request Oct 23, 2025
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: Nikhil Ghosh <nikhil@anyscale.com>
Signed-off-by: nikhil <nikhil@anyscale.com>
Co-authored-by: Nikhil Ghosh <nikhil@anyscale.com>
Co-authored-by: Nikhil G <nrghosh@users.noreply.github.com>
Signed-off-by: elliot-barn <elliot.barnwell@anyscale.com>
landscapepainter pushed a commit to landscapepainter/ray that referenced this pull request Nov 17, 2025
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: Nikhil Ghosh <nikhil@anyscale.com>
Signed-off-by: nikhil <nikhil@anyscale.com>
Co-authored-by: Nikhil Ghosh <nikhil@anyscale.com>
Co-authored-by: Nikhil G <nrghosh@users.noreply.github.com>
Aydin-ab pushed a commit to Aydin-ab/ray-aydin that referenced this pull request Nov 19, 2025
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: Nikhil Ghosh <nikhil@anyscale.com>
Signed-off-by: nikhil <nikhil@anyscale.com>
Co-authored-by: Nikhil Ghosh <nikhil@anyscale.com>
Co-authored-by: Nikhil G <nrghosh@users.noreply.github.com>
Signed-off-by: Aydin Abiar <aydin@anyscale.com>
Future-Outlier pushed a commit to Future-Outlier/ray that referenced this pull request Dec 7, 2025
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: Nikhil Ghosh <nikhil@anyscale.com>
Signed-off-by: nikhil <nikhil@anyscale.com>
Co-authored-by: Nikhil Ghosh <nikhil@anyscale.com>
Co-authored-by: Nikhil G <nrghosh@users.noreply.github.com>
Signed-off-by: Future-Outlier <eric901201@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

go add ONLY when ready to merge, run all tests llm serve Ray Serve Related Issue

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants