anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Rebase] Rebase to vllm v0.24.0 (#4709)

Browse Source
This commit is contained in:
Zhou Taichang authored and GitHub committed 2026-06-30 19:41:06 +08:00
1 parent 9a105bf90d
commit a560ed184d
60 files changed
+789 -203
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/worker/test_gpu_ar_model_runner.py
+5 -1
View File
@@ -434,8 +434,12 @@ def test_sample_tokens_tail_only_prefix_cache_uses_staged_cpu_hidden_states(monk
output = GPUARModelRunner.sample_tokens(runner, grammar_output=None)
assert output.inter_stage_outputs is None
# Non-async-chunk now ships the full payload to the next stage, so
# inter_stage_outputs mirrors multimodal_outputs (PR #4792).
assert output.inter_stage_outputs is not None
assert output.multimodal_outputs is not None
assert torch.equal(output.inter_stage_outputs[0]["hidden"], output.multimodal_outputs[0]["hidden"])
assert torch.equal(output.inter_stage_outputs[1]["hidden"], output.multimodal_outputs[1]["hidden"])
assert torch.equal(output.multimodal_outputs[0]["hidden"], torch.tensor([[1.0, 10.0]]))
assert torch.equal(
output.multimodal_outputs[1]["hidden"],