Repository navigation
[CI][Qwen3-Omni] Keep the deploy-YAML literal in the structured-config sampling check - #7803
Merged
NickCao merged 1 commit intoSep 18, 2026
Conversation
…g sampling check vllm-project#7706 and vllm-project#7742 fixed the same failing assertion in test_structured_multistage_config_reaches_runtime in two different ways and merged without a textual conflict. vllm-project#7706 changed the code2wav expectation to the runtime value (top_k=0); vllm-project#7742 kept the YAML literal and added a check that the resolver carries it verbatim plus a runtime comparison through SamplingParams normalization. Combined, the verbatim check compares 0 against the YAML's -1 and fails (main build 15599). Restore the YAML literal so the resolver check matches the typed stage config and the SamplingParams normalization still yields the runtime 0. Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
|
This PR appears to be related to model: qwen-omni. Model owners: @amy-why-3459 @yenuo26 @NickCao Routing: @amy-why-3459 via semantic router; @yenuo26 via CI owner, CODEOWNERS; @NickCao via CODEOWNERS @linyueqian, please review your own changes and leave a short self-review comment describing what you checked. PRs without author self-review may not be assigned a reviewer. Please take a look when you have a chance. If you would like an automated review, mention @vllm-omni-review-bot in a comment. |
NickCao
approved these changes
Sep 18, 2026
NickCao
enabled auto-merge (squash)
September 18, 2026 18:02
tzhouam
added a commit
that referenced
this pull request
Sep 21, 2026
Brings in 65 main commits (825ab20..ae3880f). Motivation: the three CI failures left on Buildkite #3060 are main drift, not rebase regressions: - MiniCPM-o 4.5 seed-tts perf (ready + nightly): the identical request ("Tim Tebow ..." item, 30.2 s of silence, response never reaching response.done, audio_past_key_values reset at 1500) also fails on main's own builds #3049 and #3052, and passes on main from #3054 on, after [CI/Build][MiniCPM-o] Fix the Nightly tests (#7758, 6df62d5), which the rebase branch did not carry. - Nemotron VoiceChat native-duplex e2e: main marked the test skip in the same #7758 (the pipeline declares no duplex_plugin, so /v1/realtime falls through to vLLM's speech-to-text handler and rejects session.update); main's build #3054 skipped it, ours ran it. Conflict resolutions: - tests/e2e/offline_inference/test_qwen3_omni.py: main's side. #7742/#7803 compare the deploy-YAML literal (top_k -1) verbatim and normalize the runtime check through SamplingParams, which supersedes 3dee645's top_k=0 expectation. - vllm_omni/diffusion/diffusion_kv/model_runner_backend.py: both sides dropped. Main (#7166) removed the scheduler_config.max_num_seqs override; the rebase removed the kv_caches list because f2aad6aa70's init_kv_cache returns the caches as a dict. - vllm_omni/benchmarks/patch/patch.py: main's Video-MME helpers kept together with the rebase's get_samples(args, tokenizer, **kwargs) signature; both delegate paths forward **kwargs. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
mlaneuville
pushed a commit
to mlaneuville/vllm-omni
that referenced
this pull request
Sep 22, 2026
…g sampling check (vllm-project#7803) Signed-off-by: Yueqian Lin <linyueqian@outlook.com> Signed-off-by: Matthieu Laneuville <matthieu.laneuville@surf.nl>
khairulkabir1661
pushed a commit
to khairulkabir1661/vllm-omni
that referenced
this pull request
Sep 25, 2026
…g sampling check (vllm-project#7803) Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Purpose
Omni · Qwen3-Omni Testis still red on main after #7742 (build 15599 on d4ffde1):test_structured_multistage_config_reaches_runtimenow fails at the resolver check instead of the runtime check.Root cause
#7706 and #7742 fixed the same assertion in two different ways and merged without a textual conflict:
top_k: 0.top_k: -1), added a check that the resolver carries the YAML values verbatim into the typed stage config, and compared the runtimeSamplingParamsagainstSamplingParams(**expected)so vLLM's greedy normalization applies on both sides.Combined, the verbatim check compares
0against the YAML's-1:Change
Restore the YAML literal (
top_k: -1) inexpected_samplingand say in the comment that these literals mirrorvllm_omni/deploy/qwen3_omni_moe.yaml. With that, the resolver check matches the typed stage config and the normalized runtime comparison still yieldstop_k == 0. Test-only; no runtime code touched.Validation
ruff checkandruff format --checkpass on the file.advanced_modeland only runs in the merge pipeline, so the PR lane cannot exercise it; the post-merge build is the confirmation. The failing values above are read from the build 15599 job log. This is the remaining red tracked in [CI]Omni · Qwen3-Omni Test(advanced_model) is red on main: builds 15507 and 15510, last green 15400 #7732.