diff --git a/.buildkite/cuda/rebase-pipeline.yml b/.buildkite/cuda/rebase-pipeline.yml index 064a7beaf..391079c4a 100644 --- a/.buildkite/cuda/rebase-pipeline.yml +++ b/.buildkite/cuda/rebase-pipeline.yml @@ -33,13 +33,3 @@ steps: - python3 .buildkite/common/scripts/upload_pipeline.py --upload --all .buildkite/cuda/test-nightly.yml agents: queue: "cpu_queue_premerge" - - # Include the slow model cases moved from nightly into weekly for release validation. - - label: "Upload Weekly Pipeline" - depends_on: image-build - key: upload-weekly-pipeline - if: build.env("WEEKLY") == "1" - commands: - - python3 .buildkite/common/scripts/upload_pipeline.py --upload --all .buildkite/cuda/test-weekly.yml - agents: - queue: "cpu_queue_premerge" diff --git a/tests/diffusion/quantization/test_fp8_config.py b/tests/diffusion/quantization/test_fp8_config.py index 0241c8fd1..ce0daeb58 100644 --- a/tests/diffusion/quantization/test_fp8_config.py +++ b/tests/diffusion/quantization/test_fp8_config.py @@ -1,5 +1,5 @@ # SPDX-License-Identifier: Apache-2.0 -# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project +# SPDX-FileCopyrightText: Copyright contributors to the vLLM project """Tests for the unified quantization framework.""" import pytest diff --git a/tests/engine/test_arg_utils_shared_fields.py b/tests/engine/test_arg_utils_shared_fields.py index 55f12f4ff..e5c20ccd5 100644 --- a/tests/engine/test_arg_utils_shared_fields.py +++ b/tests/engine/test_arg_utils_shared_fields.py @@ -1,5 +1,5 @@ # SPDX-License-Identifier: Apache-2.0 -# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project +# SPDX-FileCopyrightText: Copyright contributors to the vLLM project """Tests for vllm_omni.engine.arg_utils — invariants that must hold for the orchestrator/engine/server CLI flag partition.""" diff --git a/tests/engine/test_omni_request.py b/tests/engine/test_omni_request.py index 433162925..b1a5abafd 100644 --- a/tests/engine/test_omni_request.py +++ b/tests/engine/test_omni_request.py @@ -1,5 +1,5 @@ # SPDX-License-Identifier: Apache-2.0 -# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project +# SPDX-FileCopyrightText: Copyright contributors to the vLLM project """Regression tests for OmniRequest substitutability with the base Request. vllm-omni rebinds ``vllm.v1.request.Request`` to ``OmniRequest`` at import diff --git a/tests/engine/test_omni_request_output.py b/tests/engine/test_omni_request_output.py index a7c8d2764..0179a221b 100644 --- a/tests/engine/test_omni_request_output.py +++ b/tests/engine/test_omni_request_output.py @@ -1,5 +1,5 @@ # SPDX-License-Identifier: Apache-2.0 -# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project +# SPDX-FileCopyrightText: Copyright contributors to the vLLM project """Tests for OmniRequestOutput class.""" import numpy as np diff --git a/tests/engine/test_stage_engine_core_client.py b/tests/engine/test_stage_engine_core_client.py index b228055b7..37dd07bc7 100644 --- a/tests/engine/test_stage_engine_core_client.py +++ b/tests/engine/test_stage_engine_core_client.py @@ -1,5 +1,5 @@ # SPDX-License-Identifier: Apache-2.0 -# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project +# SPDX-FileCopyrightText: Copyright contributors to the vLLM project """Tests for StageEngineCoreClient.check_health().""" from __future__ import annotations diff --git a/tests/helpers/distributed.py b/tests/helpers/distributed.py index 5c9c35879..1cc79753b 100644 --- a/tests/helpers/distributed.py +++ b/tests/helpers/distributed.py @@ -29,7 +29,7 @@ def start_collective_workers( def configure_cpu_collective_worker() -> None: """Select CPU platforms inside a spawned worker that only uses Gloo. - Upstream coordinators now resolve local ranks through the selected + Upstream coordinators resolve local ranks through the selected platform's visible devices. CPU ranks can outnumber visible GPUs, so they must use the CPU platform even when the test host has CUDA installed. The worker still creates real process groups and runs real collectives. diff --git a/tests/model_executor/test_cfg_pairing.py b/tests/model_executor/test_cfg_pairing.py index 937b32b46..6d44e70dc 100644 --- a/tests/model_executor/test_cfg_pairing.py +++ b/tests/model_executor/test_cfg_pairing.py @@ -1,5 +1,5 @@ # SPDX-License-Identifier: Apache-2.0 -# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project +# SPDX-FileCopyrightText: Copyright contributors to the vLLM project """Unit tests for the model-neutral CFG request-pairing scheduler patches. The patches keep a cond/uncond request pair step-locked inside one engine: diff --git a/vllm_omni/core/sched/utils.py b/vllm_omni/core/sched/utils.py index 3bf336dc8..d346caebb 100644 --- a/vllm_omni/core/sched/utils.py +++ b/vllm_omni/core/sched/utils.py @@ -1,5 +1,5 @@ # SPDX-License-Identifier: Apache-2.0 -# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project +# SPDX-FileCopyrightText: Copyright contributors to the vLLM project """Shared utilities for omni schedulers.""" from vllm.v1.core.kv_cache_manager import KVCacheManager diff --git a/vllm_omni/model_executor/models/common/cfg_pairing.py b/vllm_omni/model_executor/models/common/cfg_pairing.py index e19ee2679..d104d6283 100644 --- a/vllm_omni/model_executor/models/common/cfg_pairing.py +++ b/vllm_omni/model_executor/models/common/cfg_pairing.py @@ -1,5 +1,5 @@ # SPDX-License-Identifier: Apache-2.0 -# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project +# SPDX-FileCopyrightText: Copyright contributors to the vLLM project # # Adapted from nvidia/Nemotron-Labs-Audex-2B (Apache-2.0): # inference_scripts_vllm/audiogen_scripts/vllm_cfg_patch.py diff --git a/vllm_omni/model_executor/models/voxcpm2/scheduler.py b/vllm_omni/model_executor/models/voxcpm2/scheduler.py index 17111c5ad..0a4504820 100644 --- a/vllm_omni/model_executor/models/voxcpm2/scheduler.py +++ b/vllm_omni/model_executor/models/voxcpm2/scheduler.py @@ -1,5 +1,5 @@ # SPDX-License-Identifier: Apache-2.0 -# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project +# SPDX-FileCopyrightText: Copyright contributors to the vLLM project from __future__ import annotations diff --git a/vllm_omni/model_executor/stage_input_processors/cosyvoice3.py b/vllm_omni/model_executor/stage_input_processors/cosyvoice3.py index 3e8af2c0a..7f3663a97 100644 --- a/vllm_omni/model_executor/stage_input_processors/cosyvoice3.py +++ b/vllm_omni/model_executor/stage_input_processors/cosyvoice3.py @@ -305,8 +305,8 @@ _FULL_PAYLOAD_REPLACE_KEYS: frozenset[str] = frozenset( } ) -# vLLM 0.31 keeps the input conditioning snapshot in the request payload and -# the talker also emits its padded snapshot. Both describe the same prompt; +# The input conditioning snapshot remains in the request payload and the +# talker also emits its padded snapshot. Both describe the same prompt; # concatenating them creates incompatible shapes before speech_token_len can # unpad the emitted value for code2wav. for _conditioning_key in _FULL_PAYLOAD_REPLACE_KEYS: