iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
patches
vLLM/.buildkite/test_areas/disaggregated.yaml
T
Jiangyun ZhuClaude Opus 5.5mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2cc2e68d1c [Core][Mamba] Remove leftovers of mamba_cache_mode="all" (#60043) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Jiangyun Zhu <zhujiangyun@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-10-13 00:58:59 -07:00

454 lines
18 KiB
YAML
Raw Permalink Blame History

group: Disaggregated
depends_on:
- image-build
steps:
- label: ":nvidia: (L4) Distributed NixlConnector PD accuracy"
key: distributed-nixlconnector-pd-accuracy-4-gpus
timeout_in_minutes: 55
working_dir: "/vllm-workspace/tests"
device: l4
num_devices: 4
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
commands:
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
mirror:
amd:
label: ":amd: (MI355) Distributed NixlConnector PD accuracy"
dind: false
device: mi355_4
timeout_in_minutes: 60
depends_on:
- image-build-amd
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
- vllm/platforms/rocm.py
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt
- ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
- label: ":nvidia: (L4) Distributed FlashInfer NixlConnector PD accuracy"
key: distributed-flashinfer-nixlconnector-pd-accuracy-4-gpus
timeout_in_minutes: 55
working_dir: "/vllm-workspace/tests"
device: l4
num_devices: 4
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
commands:
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- FLASHINFER=1 bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
mirror:
amd:
label: ":amd: (MI355) Distributed AITER NixlConnector PD accuracy"
dind: false
device: mi355_4
num_devices: 4
timeout_in_minutes: 60
working_dir: "/vllm-workspace/tests"
depends_on:
- image-build-amd
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
- tests/v1/kv_connector/rocm_pd_accuracy_utils.py
- tests/utils.py
- vllm/v1/attention/backends/rocm_aiter_unified_attn.py
- vllm/platforms/rocm.py
- requirements/common.txt
- requirements/kv_connectors_rocm.txt
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt
# Preserve all six model/TP pairs with native AITER attention.
- pytest -v -s v1/kv_connector/nixl_integration/test_accuracy_rocm.py
- label: ":nvidia: (L4) Push NixlConnector PP prefill PD accuracy"
key: push-nixlconnector-pp-prefill-pd-accuracy-4-gpus
timeout_in_minutes: 30
working_dir: "/vllm-workspace/tests"
device: l4
num_devices: 4
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
- tests/v1/kv_connector/nixl_push_integration/
commands:
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- bash v1/kv_connector/nixl_push_integration/config_sweep_accuracy_test.sh
mirror:
amd:
label: ":amd: (MI300) Push NixlConnector PP prefill PD accuracy"
dind: false
device: mi300_4
timeout_in_minutes: 55
depends_on:
- image-build-amd
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
- tests/v1/kv_connector/nixl_push_integration/
- vllm/platforms/rocm.py
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt
- ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_push_integration/config_sweep_accuracy_test.sh
- label: ":nvidia: (L4) DP EP Distributed NixlConnector PD accuracy"
key: dp-ep-distributed-nixlconnector-pd-accuracy-tests-4-gpus
timeout_in_minutes: 30
working_dir: "/vllm-workspace/tests"
device: l4
num_devices: 4
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
commands:
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- DP_EP=1 bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
mirror:
amd:
label: ":amd: (MI355) DP EP Distributed NixlConnector PD accuracy"
dind: false
device: mi355_4
timeout_in_minutes: 40
depends_on:
- image-build-amd
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
- vllm/platforms/rocm.py
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt
- DP_EP=1 ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
- label: ":nvidia: (L4) CrossLayer KV layout Distributed NixlConnector PD accuracy"
key: crosslayer-kv-layout-distributed-nixlconnector-pd-accuracy-tests-4-gpus
timeout_in_minutes: 55
working_dir: "/vllm-workspace/tests"
device: l4
num_devices: 4
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
commands:
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- CROSS_LAYERS_BLOCKS=True bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
mirror:
amd:
label: ":amd: (MI300) CrossLayer KV layout Distributed NixlConnector PD accuracy"
dind: false
device: mi300_4
timeout_in_minutes: 60
depends_on:
- image-build-amd
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
- vllm/platforms/rocm.py
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt
- CROSS_LAYERS_BLOCKS=True ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
- label: ":nvidia: (L4) Hybrid SSM NixlConnector PD accuracy"
key: hybrid-ssm-nixlconnector-pd-accuracy-tests-4-gpus
timeout_in_minutes: 60
working_dir: "/vllm-workspace/tests"
device: l4
num_devices: 4
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
commands:
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- HYBRID_SSM=1 bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
mirror:
amd:
label: ":amd: (MI300) Hybrid SSM NixlConnector PD accuracy"
dind: false
device: mi300_4
timeout_in_minutes: 80
depends_on:
- image-build-amd
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
- vllm/platforms/rocm.py
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt
- HYBRID_SSM=1 ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
- label: ":nvidia: (L4) NixlConnector PD edge case"
key: nixlconnector-pd-edge-cases-2-gpus
timeout_in_minutes: 40
working_dir: "/vllm-workspace/tests"
device: l4
num_devices: 2
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- vllm/v1/core/sched/
- tests/v1/kv_connector/nixl_integration/
env:
PREFILL_GPU_ID: "0"
DECODE_GPU_ID: "1"
commands:
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- bash v1/kv_connector/nixl_integration/run_edge_case_test.sh
mirror:
amd:
label: ":amd: (MI300) NixlConnector PD edge case"
dind: false
device: mi300_2
timeout_in_minutes: 65
depends_on:
- image-build-amd
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- vllm/v1/core/sched/
- tests/v1/kv_connector/nixl_integration/
- vllm/platforms/rocm.py
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt
- PREFILL_GPU_ID=0 DECODE_GPU_ID=1 ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_integration/run_edge_case_test.sh
- label: ":nvidia: (L4) Hybrid SSM NixlConnector PD prefix cache"
key: hybrid-ssm-nixlconnector-pd-prefix-cache-2-gpus
timeout_in_minutes: 25
working_dir: "/vllm-workspace/tests"
device: l4
num_devices: 2
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- vllm/v1/core/sched/
- vllm/v1/core/kv_cache_coordinator.py
- tests/v1/kv_connector/nixl_integration/
commands:
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- bash v1/kv_connector/nixl_integration/run_mamba_prefix_cache_test.sh
mirror:
amd:
label: ":amd: (MI355) Hybrid SSM NixlConnector PD prefix cache"
dind: false
device: mi355_2
timeout_in_minutes: 25
depends_on:
- image-build-amd
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- vllm/v1/core/sched/
- vllm/v1/core/kv_cache_coordinator.py
- tests/v1/kv_connector/nixl_integration/
- vllm/platforms/rocm.py
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt
- ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_integration/run_mamba_prefix_cache_test.sh
- label: ":nvidia: (L4) MultiConnector (Nixl+Offloading) PD accuracy"
key: multiconnector-nixl-offloading-pd-accuracy-2-gpus
timeout_in_minutes: 40
working_dir: "/vllm-workspace/tests"
device: l4
num_devices: 2
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py
- vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py
- vllm/distributed/kv_transfer/kv_connector/v1/offloading/
- tests/v1/kv_connector/nixl_integration/
commands:
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- bash v1/kv_connector/nixl_integration/run_multi_connector_accuracy_test.sh
mirror:
amd:
label: ":amd: (MI355) MultiConnector (Nixl+Offloading) PD accuracy"
dind: false
device: mi355_2
timeout_in_minutes: 40
depends_on:
- image-build-amd
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py
- vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py
- vllm/distributed/kv_transfer/kv_connector/v1/offloading/
- tests/v1/kv_connector/nixl_integration/
- requirements/kv_connectors_rocm.txt
- vllm/platforms/rocm.py
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt
- ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_integration/run_multi_connector_accuracy_test.sh
- label: ":nvidia: (A100) NixlConnector PD + Spec Decode acceptance"
key: nixlconnector-pd-spec-decode-acceptance-2-gpus
timeout_in_minutes: 45
device: a100
working_dir: "/vllm-workspace/tests"
num_devices: 2
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- vllm/v1/worker/kv_connector_model_runner_mixin.py
- tests/v1/kv_connector/nixl_integration/
commands:
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- bash v1/kv_connector/nixl_integration/config_sweep_spec_decode_test.sh
mirror:
amd:
label: ":amd: (MI355) NixlConnector PD + Spec Decode acceptance"
dind: false
device: mi355_2
timeout_in_minutes: 45
depends_on:
- image-build-amd
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- vllm/v1/worker/kv_connector_model_runner_mixin.py
- tests/v1/kv_connector/nixl_integration/
- vllm/platforms/rocm.py
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt
- KV_CACHE_MEMORY_BYTES=8G ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_integration/config_sweep_spec_decode_test.sh
- label: ":nvidia: (L4) MultiConnector (Nixl+Offloading) PD edge cases"
key: multiconnector-nixl-offloading-pd-edge-cases-2-gpus
timeout_in_minutes: 25
working_dir: "/vllm-workspace/tests"
device: l4
num_devices: 2
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py
- vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py
- vllm/distributed/kv_transfer/kv_connector/v1/offloading/
- tests/v1/kv_connector/nixl_integration/
commands:
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- bash v1/kv_connector/nixl_integration/run_multi_connector_edge_case_test.sh
mirror:
amd:
label: ":amd: (MI355) MultiConnector (Nixl+Offloading) PD edge cases"
dind: false
device: mi355_2
timeout_in_minutes: 25
depends_on:
- image-build-amd
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py
- vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py
- vllm/distributed/kv_transfer/kv_connector/v1/offloading/
- tests/v1/kv_connector/nixl_integration/
- vllm/platforms/rocm.py
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt
- ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_integration/run_multi_connector_edge_case_test.sh
# P TP 4 - D DPEP 4 test case for DSv4-Flash
- label: ":nvidia: (H200) DSv4-Flash Disaggregated DP EP"
key: dsv4-flash-disaggregated
timeout_in_minutes: 60
device: h200
optional: true
working_dir: "/vllm-workspace/tests"
num_devices: 8
env:
ENABLE_HMA_FLAG: "1"
DP_EP: "1"
GPU_MEMORY_UTILIZATION: "0.85"
PREFILLER_TP_SIZE: "4"
DECODER_TP_SIZE: "4"
PREFILL_BLOCK_SIZE: "256"
DECODE_BLOCK_SIZE: "256"
MODEL_NAMES: "deepseek-ai/DeepSeek-V4-Flash"
VLLM_ENGINE_READY_TIMEOUT_S: "1800"
VLLM_SERVE_EXTRA_ARGS: "--trust-remote-code,--kv-cache-dtype,fp8"
# The V4 indexer only supports block-outermost layouts; let it pick.
PREFILLER_KV_LAYOUT: ""
DECODER_KV_LAYOUT: ""
commands:
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- bash v1/kv_connector/nixl_integration/run_accuracy_test.sh
mirror:
amd:
label: ":amd: (MI355) DSv4-Flash Disaggregated DP EP"
dind: false
device: mi355_8
timeout_in_minutes: 85
depends_on:
- image-build-amd
source_file_dependencies:
- requirements/kv_connectors_rocm.txt
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- vllm/model_executor/layers/fused_moe/
- vllm/model_executor/layers/quantization/
- vllm/models/deepseek_v4/
- vllm/v1/attention/
- tests/v1/kv_connector/nixl_integration/
- vllm/_aiter_ops.py
- vllm/platforms/rocm.py
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt
# A mirror does not inherit the parent env, so it is repeated here in
# the parent's order. The layouts must stay empty: unset, the script
# defaults to HND, which the V4 indexer rejects.
- >-
VLLM_ROCM_USE_AITER=1
ENABLE_HMA_FLAG=1
DP_EP=1
GPU_MEMORY_UTILIZATION=0.85
PREFILLER_TP_SIZE=4
DECODER_TP_SIZE=4
PREFILL_BLOCK_SIZE=256
DECODE_BLOCK_SIZE=256
MODEL_NAMES=deepseek-ai/DeepSeek-V4-Flash
VLLM_ENGINE_READY_TIMEOUT_S=1800
VLLM_SERVE_EXTRA_ARGS=--trust-remote-code,--kv-cache-dtype,fp8
PREFILLER_KV_LAYOUT=
DECODER_KV_LAYOUT=
bash v1/kv_connector/nixl_integration/run_accuracy_test.sh
- label: ":nvidia: (H200) Kimi-Linear-48B-A3B Disaggregated DP EP"
key: kimi-linear-disaggregated
timeout_in_minutes: 60
device: h200
optional: true
working_dir: "/vllm-workspace/tests"
num_devices: 4
env:
ENABLE_HMA_FLAG: "1"
DP_EP: "1"
GPU_MEMORY_UTILIZATION: "0.9"
VLLM_SSM_CONV_STATE_LAYOUT: "DS"
PREFILLER_TP_SIZE: "2"
DECODER_TP_SIZE: "2"
MODEL_NAMES: "moonshotai/Kimi-Linear-48B-A3B-Instruct"
# Keep TP=2 prefill and TP=1 decode above both hybrid page-size minima.
PREFILL_BLOCK_SIZE: "2048"
DECODE_BLOCK_SIZE: "2048"
VLLM_SERVE_EXTRA_ARGS: "--trust-remote-code,--max-model-len 32768"
commands:
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
- bash v1/kv_connector/nixl_integration/run_accuracy_test.sh
mirror:
amd:
label: ":amd: (MI355) Kimi-Linear-48B-A3B Disaggregated DP EP"
dind: false
device: mi355_4
num_devices: 4
timeout_in_minutes: 105
working_dir: /vllm-workspace/tests
depends_on:
- image-build-amd
source_file_dependencies:
- vllm/platforms/rocm.py
- vllm/models/kimi_k3/
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
- tests/v1/kv_connector/nixl_integration/
- requirements/kv_connectors_rocm.txt
env:
VLLM_WORKER_MULTIPROC_METHOD: "spawn"
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt
- bash v1/kv_connector/nixl_integration/run_accuracy_test.sh
Reference in New Issue View Git Blame Copy Permalink