Merge tag 'v0.14.0rc0' into v0.14.0rc0-ori

.buildkite/scripts/hardware_ci/run-amd-test.sh

@@ -141,7 +141,6 @@ if [[ $commands == *" entrypoints/openai "* ]]; then
   --ignore=entrypoints/openai/test_audio.py \
   --ignore=entrypoints/openai/test_shutdown.py \
   --ignore=entrypoints/openai/test_completion.py \
-  --ignore=entrypoints/openai/test_sleep.py \
   --ignore=entrypoints/openai/test_models.py \
   --ignore=entrypoints/openai/test_lora_adapters.py \
   --ignore=entrypoints/openai/test_return_tokens_as_ids.py \

.buildkite/scripts/hardware_ci/run-cpu-test.sh

@@ -50,6 +50,7 @@ function cpu_tests() {
   docker exec cpu-test-"$NUMA_NODE" bash -c "
     set -e
     pytest -x -v -s tests/kernels/attention/test_cpu_attn.py
+    pytest -x -v -s tests/kernels/moe/test_cpu_fused_moe.py
     pytest -x -v -s tests/kernels/test_onednn.py"
 
   # Run basic model test

.buildkite/scripts/hardware_ci/run-xpu-test.sh

@@ -39,7 +39,7 @@ docker run \
     python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend ray
     python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp
     python3 examples/offline_inference/basic/generate.py --model Intel/Qwen2.5-0.5B-W4A16-G128-AutoRound-LLMC-TEST-ONLY --enforce-eager
-    VLLM_ATTENTION_BACKEND=TRITON_ATTN python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager
+    python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --attention-backend=TRITON_ATTN
     cd tests
     pytest -v -s v1/core
     pytest -v -s v1/engine

.buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_block_ep_eplb.sh

@@ -44,10 +44,10 @@ trap cleanup EXIT
 
 for BACK in "${BACKENDS[@]}"; do
   VLLM_DEEP_GEMM_WARMUP=skip \
-  VLLM_ALL2ALL_BACKEND=$BACK \
   vllm serve "$MODEL" \
     --enforce-eager \
     --enable-eplb \
+    --all2all-backend $BACK \
     --eplb-config '{"window_size":10, "step_interval":100, "num_redundant_experts":0, "log_balancedness":true}' \
     --tensor-parallel-size ${TENSOR_PARALLEL_SIZE} \
     --data-parallel-size ${DATA_PARALLEL_SIZE} \

.buildkite/scripts/scheduled_integration_test/qwen3_next_mtp_async_eplb.sh

@@ -43,12 +43,12 @@ trap cleanup EXIT
 
 for BACK in "${BACKENDS[@]}"; do
   VLLM_DEEP_GEMM_WARMUP=skip \
-  VLLM_ALL2ALL_BACKEND=$BACK \
   vllm serve "$MODEL" \
     --enforce-eager \
     --tensor-parallel-size 4 \
     --enable-expert-parallel \
     --enable-eplb \
+    --all2all-backend $BACK \
     --eplb-config '{"window_size":200,"step_interval":600,"use_async":true}' \
     --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":1}' \
     --trust-remote-code \

.buildkite/test-amd.yaml

@@ -128,7 +128,7 @@ steps:
   - tests/entrypoints/
   commands:
   - pytest -v -s entrypoints/openai/tool_parsers
-  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling
+  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/openai --ignore=entrypoints/rpc --ignore=entrypoints/sleep --ignore=entrypoints/instrumentator --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling
 
 - label: Entrypoints Integration Test (LLM) # 30min
   timeout_in_minutes: 40
@@ -148,7 +148,7 @@ steps:
   - pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process
   - pytest -v -s entrypoints/offline_mode # Needs to avoid interference with other tests
 
-- label: Entrypoints Integration Test (API Server) # 100min
+- label: Entrypoints Integration Test (API Server 1) # 100min
   timeout_in_minutes: 130
   mirror_hardwares: [amdexperimental]
   agent_pool: mi325_1
@@ -162,10 +162,28 @@ steps:
   - tests/entrypoints/test_chat_utils
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/openai/test_collective_rpc.py # PYTHONPATH is needed to import custom Worker extension
-  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/test_collective_rpc.py --ignore=entrypoints/openai/tool_parsers/
+  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/
   - pytest -v -s entrypoints/test_chat_utils.py
 
+- label: Entrypoints Integration Test (API Server 2)
+  timeout_in_minutes: 50
+  mirror_hardwares: [amdexperimental]
+  agent_pool: mi325_1
+  # grade: Blocking
+  working_dir: "/vllm-workspace/tests"
+  fast_check: true
+  torch_nightly: true
+  source_file_dependencies:
+  - vllm/
+  - tests/entrypoints/sleep
+  - tests/entrypoints/rpc
+  - tests/tool_use
+  commands:
+  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+  - pytest -v -s entrypoints/sleep
+  - pytest -v -s tool_use
+  - PYTHONPATH=/vllm-workspace  pytest -v -s entrypoints/rpc
+
 - label: Entrypoints Integration Test (Pooling)
   timeout_in_minutes: 50
   mirror_hardwares: [amdexperimental]
@@ -722,7 +740,7 @@ steps:
   # https://github.com/pytorch/ao/issues/2919, we'll have to skip new torchao tests for now
   # we can only upgrade after this is resolved
   # TODO(jerryzh168): resolve the above comment
-  - uv pip install --system torchao==0.13.0
+  - uv pip install --system torchao==0.14.1
   - uv pip install --system conch-triton-kernels
   - VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py
 
@@ -736,7 +754,7 @@ steps:
   - vllm/model_executor/layers/quantization
   autorun_on_main: true
   commands:
-  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt --tp-size=1
+  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt
 
 - label: OpenAI API correctness # 10min
   timeout_in_minutes: 15
@@ -751,17 +769,6 @@ steps:
   # Transcription WER check is skipped because encoder-decoder models are not supported on ROCm, see https://github.com/vllm-project/vllm/issues/27442
   - pytest -s entrypoints/openai/correctness/
 
-- label: OpenAI-Compatible Tool Use # 23 min
-  timeout_in_minutes: 35
-  mirror_hardwares: [amdexperimental, amdproduction]
-  agent_pool: mi325_1
-  # grade: Blocking
-  fast_check: false
-  source_file_dependencies:
-    - vllm/
-    - tests/tool_use
-  commands:
-    - pytest -v -s tool_use
 
 #####  models test  #####
 
@@ -1196,7 +1203,7 @@ steps:
   - csrc/
   - vllm/model_executor/layers/quantization
   commands:
-  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt --tp-size=1
+  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt
 
 #####  1 GPU test  #####
 #####  multi gpus test  #####
@@ -1490,7 +1497,7 @@ steps:
     - "VLLM_TEST_CLEAN_GPU_MEMORY=1 pytest -v -s tests/compile/distributed/test_fusions_e2e.py -k 'not Llama-4'"
     - VLLM_TEST_CLEAN_GPU_MEMORY=1 pytest -v -s tests/distributed/test_sequence_parallel.py
     - pytest -v -s tests/distributed/test_context_parallel.py
-    - HIP_VISIBLE_DEVICES=0,1 VLLM_ALL2ALL_BACKEND=deepep_high_throughput VLLM_USE_DEEP_GEMM=1 VLLM_LOGGING_LEVEL=DEBUG python3 examples/offline_inference/data_parallel.py --model Qwen/Qwen1.5-MoE-A2.7B --tp-size=1  --dp-size=2 --max-model-len 2048
+    - HIP_VISIBLE_DEVICES=0,1 VLLM_USE_DEEP_GEMM=1 VLLM_LOGGING_LEVEL=DEBUG python3 examples/offline_inference/data_parallel.py --model Qwen/Qwen1.5-MoE-A2.7B --tp-size=1 --dp-size=2 --max-model-len 2048 --all2all-backend deepep_high_throughput
     - pytest -v -s tests/v1/distributed/test_dbo.py
 
 ##### B200 test #####
@@ -1514,7 +1521,7 @@ steps:
   - csrc/
   - vllm/model_executor/layers/quantization
   commands:
-  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt --tp-size=1
+  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt
 
 - label: LM Eval Large Models (4 Card)
   mirror_hardwares: [amdexperimental, amdproduction]

.buildkite/test-pipeline.yaml

@@ -114,7 +114,7 @@ steps:
   - tests/entrypoints/
   commands:
   - pytest -v -s entrypoints/openai/tool_parsers
-  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling
+  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/rpc --ignore=entrypoints/sleep --ignore=entrypoints/instrumentator --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling
 
 - label: Entrypoints Integration Test (LLM) # 30min
   timeout_in_minutes: 40
@@ -132,7 +132,7 @@ steps:
   - pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process
   - pytest -v -s entrypoints/offline_mode # Needs to avoid interference with other tests
 
-- label: Entrypoints Integration Test (API Server) # 100min
+- label: Entrypoints Integration Test (API Server 1) # 100min
   timeout_in_minutes: 130
   mirror_hardwares: [amdexperimental]
   working_dir: "/vllm-workspace/tests"
@@ -144,10 +144,26 @@ steps:
   - tests/entrypoints/test_chat_utils
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/openai/test_collective_rpc.py # PYTHONPATH is needed to import custom Worker extension
-  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/test_collective_rpc.py --ignore=entrypoints/openai/tool_parsers/
+  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/  --ignore=entrypoints/openai/tool_parsers/
   - pytest -v -s entrypoints/test_chat_utils.py
 
+- label: Entrypoints Integration Test (API Server 2)
+  timeout_in_minutes: 50
+  mirror_hardwares: [amdexperimental]
+  working_dir: "/vllm-workspace/tests"
+  fast_check: true
+  torch_nightly: true
+  source_file_dependencies:
+  - vllm/
+  - tests/entrypoints/sleep
+  - tests/entrypoints/rpc
+  - tests/tool_use
+  commands:
+  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+  - pytest -v -s entrypoints/sleep
+  - PYTHONPATH=/vllm-workspace  pytest -v -s entrypoints/rpc
+  - pytest -v -s tool_use
+
 - label: Entrypoints Integration Test (Pooling)
   timeout_in_minutes: 50
   mirror_hardwares: [amdexperimental]
@@ -303,7 +319,10 @@ steps:
     # TODO: accuracy does not match, whether setting
     # VLLM_USE_FLASHINFER_SAMPLER or not on H100.
     - pytest -v -s v1/e2e
-    - pytest -v -s v1/engine
+    # Run this test standalone for now;
+    # need to untangle use (implicit) use of spawn/fork across the tests.
+    - pytest -v -s v1/engine/test_preprocess_error_handling.py
+    - pytest -v -s v1/engine --ignore v1/engine/test_preprocess_error_handling.py
 
 - label: V1 Test entrypoints # 35min
   timeout_in_minutes: 50
@@ -642,7 +661,7 @@ steps:
   # https://github.com/pytorch/ao/issues/2919, we'll have to skip new torchao tests for now
   # we can only upgrade after this is resolved
   # TODO(jerryzh168): resolve the above comment
-  - uv pip install --system torchao==0.13.0 --index-url https://download.pytorch.org/whl/cu129
+  - uv pip install --system torchao==0.14.1 --index-url https://download.pytorch.org/whl/cu129
   - uv pip install --system conch-triton-kernels
   - VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py
 
@@ -654,7 +673,7 @@ steps:
   - vllm/model_executor/layers/quantization
   autorun_on_main: true
   commands:
-  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt --tp-size=1
+  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt
 
 - label: OpenAI API correctness # 22min
   timeout_in_minutes: 30
@@ -666,16 +685,6 @@ steps:
   commands: # LMEval+Transcription WER check
   - pytest -s entrypoints/openai/correctness/
 
-- label: OpenAI-Compatible Tool Use # 23 min
-  timeout_in_minutes: 35
-  mirror_hardwares: [amdexperimental]
-  fast_check: false
-  source_file_dependencies:
-    - vllm/
-    - tests/tool_use
-  commands:
-    - pytest -v -s tool_use
-
 #####  models test  #####
 
 - label: Basic Models Tests (Initialization)
@@ -1064,7 +1073,7 @@ steps:
   - csrc/
   - vllm/model_executor/layers/quantization
   commands:
-  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt --tp-size=1
+  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt
 
 #####  1 GPU test  #####
 #####  multi gpus test  #####
@@ -1325,7 +1334,7 @@ steps:
     - "VLLM_TEST_CLEAN_GPU_MEMORY=1 pytest -v -s tests/compile/distributed/test_fusions_e2e.py -k 'not Llama-4'"
     - VLLM_TEST_CLEAN_GPU_MEMORY=1 pytest -v -s tests/distributed/test_sequence_parallel.py
     - pytest -v -s tests/distributed/test_context_parallel.py
-    - CUDA_VISIBLE_DEVICES=1,2 VLLM_ALL2ALL_BACKEND=deepep_high_throughput VLLM_USE_DEEP_GEMM=1 VLLM_LOGGING_LEVEL=DEBUG python3 examples/offline_inference/data_parallel.py --model Qwen/Qwen1.5-MoE-A2.7B --tp-size=1  --dp-size=2 --max-model-len 2048
+    - CUDA_VISIBLE_DEVICES=1,2 VLLM_USE_DEEP_GEMM=1 VLLM_LOGGING_LEVEL=DEBUG python3 examples/offline_inference/data_parallel.py --model Qwen/Qwen1.5-MoE-A2.7B --tp-size=1 --dp-size=2 --max-model-len 2048 --all2all-backend deepep_high_throughput
     - pytest -v -s tests/v1/distributed/test_dbo.py
 
 ##### B200 test #####

.buildkite/test_areas/distributed.yaml

@@ -145,7 +145,7 @@ steps:
     - VLLM_TEST_CLEAN_GPU_MEMORY=1 pytest -v -s tests/compile/distributed/test_fusions_e2e.py -k 'not Llama-4'
     - VLLM_TEST_CLEAN_GPU_MEMORY=1 pytest -v -s tests/distributed/test_sequence_parallel.py
     - pytest -v -s tests/distributed/test_context_parallel.py
-    - CUDA_VISIBLE_DEVICES=1,2 VLLM_ALL2ALL_BACKEND=deepep_high_throughput VLLM_USE_DEEP_GEMM=1 VLLM_LOGGING_LEVEL=DEBUG python3 examples/offline_inference/data_parallel.py --model Qwen/Qwen1.5-MoE-A2.7B --tp-size=1  --dp-size=2 --max-model-len 2048
+    - CUDA_VISIBLE_DEVICES=1,2 VLLM_USE_DEEP_GEMM=1 VLLM_LOGGING_LEVEL=DEBUG python3 examples/offline_inference/data_parallel.py --model Qwen/Qwen1.5-MoE-A2.7B --tp-size=1 --dp-size=2 --max-model-len 2048 --all2all-backend deepep_high_throughput
     - pytest -v -s tests/v1/distributed/test_dbo.py
 
 - label: Distributed Tests (2 GPUs)(B200)

.buildkite/test_areas/e2e_integration.yaml

@@ -32,6 +32,7 @@ steps:
 - label: Prime-RL Integration (2 GPUs)
   timeout_in_minutes: 30
   optional: true
+  soft_fail: true
   num_gpus: 2
   working_dir: "/vllm-workspace"
   source_file_dependencies:
@@ -39,21 +40,3 @@ steps:
   - .buildkite/scripts/run-prime-rl-test.sh
   commands:
     - bash .buildkite/scripts/run-prime-rl-test.sh
-
-- label: DeepSeek V2-Lite Async EPLB Accuracy
-  timeout_in_minutes: 60
-  gpu: h100
-  optional: true
-  num_gpus: 4
-  working_dir: "/vllm-workspace"
-  commands:
-  - bash .buildkite/scripts/scheduled_integration_test/deepseek_v2_lite_ep_async_eplb.sh 0.25 1319 8030
-
-- label: Qwen3-Next-80B-A3B-Instruct MTP Async EPLB Accuracy
-  timeout_in_minutes: 60
-  gpu: h100
-  optional: true
-  num_gpus: 4
-  working_dir: "/vllm-workspace"
-  commands:
-  - bash .buildkite/scripts/scheduled_integration_test/qwen3_next_mtp_async_eplb.sh 0.8 1319 8040

.buildkite/test_areas/entrypoints.yaml

@@ -10,7 +10,7 @@ steps:
   - tests/entrypoints/
   commands:
   - pytest -v -s entrypoints/openai/tool_parsers
-  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling
+  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/rpc --ignore=entrypoints/sleep --ignore=entrypoints/instrumentator --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling
 
 - label: Entrypoints Integration (LLM)
   timeout_in_minutes: 40
@@ -25,7 +25,7 @@ steps:
   - pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process
   - pytest -v -s entrypoints/offline_mode # Needs to avoid interference with other tests
 
-- label: Entrypoints Integration (API Server)
+- label: Entrypoints Integration (API Server 1)
   timeout_in_minutes: 130
   working_dir: "/vllm-workspace/tests"
   source_file_dependencies:
@@ -34,11 +34,26 @@ steps:
   - tests/entrypoints/test_chat_utils
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/openai/test_collective_rpc.py # PYTHONPATH is needed to import custom Worker extension
-  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/test_collective_rpc.py --ignore=entrypoints/openai/tool_parsers/
+  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/  --ignore=entrypoints/openai/tool_parsers/
   - pytest -v -s entrypoints/test_chat_utils.py
 
 
+- label: Entrypoints Integration (API Server 2)
+  timeout_in_minutes: 130
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/
+  - tests/tool_use
+  - tests/entrypoints/sleep
+  - tests/entrypoints/instrumentator
+  - tests/entrypoints/rpc
+  commands:
+  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+  - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/rpc
+  - pytest -v -s entrypoints/instrumentator
+  - pytest -v -s entrypoints/sleep
+  - pytest -v -s tool_use
+
 - label: Entrypoints Integration (Pooling)
   timeout_in_minutes: 50
   working_dir: "/vllm-workspace/tests"

.buildkite/test_areas/lm_eval.yaml

@@ -9,7 +9,7 @@ steps:
   - vllm/model_executor/layers/quantization
   autorun_on_main: true
   commands:
-  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt --tp-size=1
+  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt
 
 - label: LM Eval Large Models (4 GPUs)(A100)
   gpu: a100
@@ -43,4 +43,4 @@ steps:
   - csrc/
   - vllm/model_executor/layers/quantization
   commands:
-  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt --tp-size=1
+  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt

.buildkite/test_areas/lora.yaml

@@ -22,6 +22,8 @@ steps:
     # FIXIT: find out which code initialize cuda before running the test
     # before the fix, we need to use spawn to test it
     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    # Alot of these tests are on the edge of OOMing
+    - export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
     # There is some Tensor Parallelism related processing logic in LoRA that
     # requires multi-GPU testing for validation.
     - pytest -v -s -x lora/test_chatglm3_tp.py

.buildkite/test_areas/models_basic.yaml

@@ -9,6 +9,7 @@ steps:
   source_file_dependencies:
   - vllm/
   - tests/models/test_initialization.py
+  - tests/models/registry.py
   commands:
     # Run a subset of model initialization tests
     - pytest -v -s models/test_initialization.py::test_can_initialize_small_subset
@@ -20,6 +21,7 @@ steps:
   source_file_dependencies:
   - vllm/model_executor/models/
   - tests/models/test_initialization.py
+  - tests/models/registry.py
   commands:
     # Only when vLLM model source is modified - test initialization of a large
     # subset of supported models (the complement of the small subset in the above

.buildkite/test_areas/pytorch.yaml

@@ -13,7 +13,9 @@ steps:
   # tests covered elsewhere.
   # Use `find` to launch multiple instances of pytest so that
   # they do not suffer from https://github.com/vllm-project/vllm/issues/28965
-  - "find compile/ -maxdepth 1 -name 'test_*.py' -exec pytest -s -v {} \\;"
+  # However, find does not normally propagate error codes, so we combine it with xargs
+  # (using -0 for proper path handling)
+  - "find compile/ -maxdepth 1 -name 'test_*.py' -print0 | xargs -0 -n1 -I{} pytest -s -v '{}'"
 
 - label: PyTorch Fullgraph Smoke Test
   timeout_in_minutes: 30

.buildkite/test_areas/tool_use.yaml

-group: Tool use
-depends_on: 
-  - image-build
-steps:
-- label: OpenAI-Compatible Tool Use
-  timeout_in_minutes: 35
-  mirror_hardwares: [amdexperimental]
-  fast_check: false
-  source_file_dependencies:
-    - vllm/
-    - tests/tool_use
-  commands:
-    - pytest -v -s tool_use

.github/mergify.yml

@@ -235,6 +235,20 @@ pull_request_rules:
       add:
         - rocm
 
+- name: label-cpu
+  description: Automatically apply cpu label
+  conditions:
+    - label != stale
+    - files~=^(?!.*kv_offload)(?!.*cpu_offload).*\bcpu.*
+  actions:
+    label:
+      add:
+        - cpu
+    assign:
+      users:
+        - "fadara01"
+        - "aditew01"
+
 - name: label-structured-output
   description: Automatically apply structured-output label
   conditions:
@@ -335,6 +349,18 @@ pull_request_rules:
       add:
         - tool-calling
 
+- name: auto-rebase if approved, ready, and 40 commits behind main
+  conditions:
+    - base = main
+    - label=ready
+    - "#approved-reviews-by >= 1"
+    - "#commits-behind >= 40"
+    - -closed
+    - -draft
+    - -conflict
+  actions:
+    rebase: {}
+
 - name: ping author on conflicts and add 'needs-rebase' label
   conditions:
     - label != stale

CMakeLists.txt

@@ -56,8 +56,8 @@ endif()
 # requirements.txt files and should be kept consistent.  The ROCm torch
 # versions are derived from docker/Dockerfile.rocm
 #
-set(TORCH_SUPPORTED_VERSION_CUDA "2.9.0")
-set(TORCH_SUPPORTED_VERSION_ROCM "2.9.0")
+set(TORCH_SUPPORTED_VERSION_CUDA "2.9.1")
+set(TORCH_SUPPORTED_VERSION_ROCM "2.9.1")
 
 #
 # Try to find python package with an executable that exactly matches
@@ -358,6 +358,8 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
 
   # marlin arches for fp16 output
   cuda_archs_loose_intersection(MARLIN_ARCHS "8.0+PTX" "${CUDA_ARCHS}")
+  # marlin has limited support for turing
+  cuda_archs_loose_intersection(MARLIN_SM75_ARCHS "7.5" "${CUDA_ARCHS}")
   # marlin arches for bf16 output (we need 9.0 for bf16 atomicAdd PTX)
   cuda_archs_loose_intersection(MARLIN_BF16_ARCHS "8.0+PTX;9.0+PTX" "${CUDA_ARCHS}")
   # marlin arches for fp8 input
@@ -365,8 +367,10 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
   # - sm90 and sm100 don't support QMMA.16832.F32.E4M3.E4M3 SAAS instruction
   # so we only enable fp8 computation for SM89 (e.g. RTX 40x0)  and 12.0 (e.g. RTX 50x0)
   cuda_archs_loose_intersection(MARLIN_FP8_ARCHS "8.9;12.0" "${CUDA_ARCHS}")
+  # marlin arches for other files
+  cuda_archs_loose_intersection(MARLIN_OTHER_ARCHS "7.5;8.0+PTX" "${CUDA_ARCHS}")
 
-  if (MARLIN_ARCHS)
+  if (MARLIN_OTHER_ARCHS)
 
     #
     # For the Marlin kernels we automatically generate sources for various
@@ -407,6 +411,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
       message(STATUS "Marlin generation script has not changed, skipping generation.")
     endif()
 
+    if (MARLIN_ARCHS)
       file(GLOB MARLIN_TEMPLATE_KERNEL_SRC "csrc/quantization/gptq_marlin/sm80_kernel_*_float16.cu")
       set_gencode_flags_for_srcs(
         SRCS "${MARLIN_TEMPLATE_KERNEL_SRC}"
@@ -426,6 +431,19 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
           PROPERTIES COMPILE_FLAGS "-static-global-template-stub=false")
       endif()
       list(APPEND VLLM_EXT_SRC ${MARLIN_TEMPLATE_BF16_KERNEL_SRC})
+    endif()
+
+    if (MARLIN_SM75_ARCHS) 
+      file(GLOB MARLIN_TEMPLATE_SM75_KERNEL_SRC "csrc/quantization/gptq_marlin/sm75_kernel_*.cu")
+      set_gencode_flags_for_srcs(
+        SRCS "${MARLIN_TEMPLATE_SM75_KERNEL_SRC}"
+        CUDA_ARCHS "${MARLIN_SM75_ARCHS}")
+      if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
+        set_source_files_properties(${MARLIN_TEMPLATE_SM75_KERNEL_SRC}
+          PROPERTIES COMPILE_FLAGS "-static-global-template-stub=false")
+      endif()
+      list(APPEND VLLM_EXT_SRC ${MARLIN_TEMPLATE_SM75_KERNEL_SRC})
+    endif()
 
     if (MARLIN_FP8_ARCHS) 
       file(GLOB MARLIN_TEMPLATE_FP8_KERNEL_SRC "csrc/quantization/gptq_marlin/sm89_kernel_*.cu")
@@ -447,14 +465,14 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
        "csrc/quantization/gptq_marlin/awq_marlin_repack.cu")
     set_gencode_flags_for_srcs(
       SRCS "${MARLIN_SRCS}"
-      CUDA_ARCHS "${MARLIN_ARCHS}")
+      CUDA_ARCHS "${MARLIN_OTHER_ARCHS}")
     if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
-      set_source_files_properties("csrc/quantization/gptq_marlin/gptq_marlin.cu"
+      set_source_files_properties(${MARLIN_SRCS}
         PROPERTIES COMPILE_FLAGS "-static-global-template-stub=false")
     endif()
     list(APPEND VLLM_EXT_SRC "${MARLIN_SRCS}")
 
-    message(STATUS "Building Marlin kernels for archs: ${MARLIN_ARCHS}")
+    message(STATUS "Building Marlin kernels for archs: ${MARLIN_OTHER_ARCHS}")
   else()
     message(STATUS "Not building Marlin kernels as no compatible archs found"
                    " in CUDA target architectures")
@@ -981,12 +999,16 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
   # note that we always set `use_atomic_add=False` for moe marlin now,
   # so we don't need 9.0 for bf16 atomicAdd PTX
   cuda_archs_loose_intersection(MARLIN_MOE_ARCHS "8.0+PTX" "${CUDA_ARCHS}")
+  # moe marlin has limited support for turing
+  cuda_archs_loose_intersection(MARLIN_MOE_SM75_ARCHS "7.5" "${CUDA_ARCHS}")
   # moe marlin arches for fp8 input
   # - sm80 doesn't support fp8 computation
   # - sm90 and sm100 don't support QMMA.16832.F32.E4M3.E4M3 SAAS instruction
   # so we only enable fp8 computation for SM89 (e.g. RTX 40x0)  and 12.0 (e.g. RTX 50x0)
   cuda_archs_loose_intersection(MARLIN_MOE_FP8_ARCHS "8.9;12.0" "${CUDA_ARCHS}")
-  if (MARLIN_MOE_ARCHS)
+  # moe marlin arches for other files
+  cuda_archs_loose_intersection(MARLIN_MOE_OTHER_ARCHS "7.5;8.0+PTX" "${CUDA_ARCHS}")
+  if (MARLIN_MOE_OTHER_ARCHS)
 
     #
     # For the Marlin MOE kernels we automatically generate sources for various
@@ -1027,8 +1049,8 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
       message(STATUS "Marlin MOE generation script has not changed, skipping generation.")
     endif()
 
+    if (MARLIN_MOE_ARCHS)
       file(GLOB MARLIN_MOE_SRC "csrc/moe/marlin_moe_wna16/sm80_kernel_*.cu")
-    list(APPEND MARLIN_MOE_SRC "csrc/moe/marlin_moe_wna16/ops.cu")
       set_gencode_flags_for_srcs(
         SRCS "${MARLIN_MOE_SRC}"
         CUDA_ARCHS "${MARLIN_MOE_ARCHS}")
@@ -1037,6 +1059,19 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
           PROPERTIES COMPILE_FLAGS "-static-global-template-stub=false")
       endif()
       list(APPEND VLLM_MOE_EXT_SRC ${MARLIN_MOE_SRC})
+    endif()
+
+    if (MARLIN_MOE_SM75_ARCHS) 
+      file(GLOB MARLIN_MOE_SM75_SRC "csrc/moe/marlin_moe_wna16/sm75_kernel_*.cu")
+      set_gencode_flags_for_srcs(
+        SRCS "${MARLIN_MOE_SM75_SRC}"
+        CUDA_ARCHS "${MARLIN_MOE_SM75_ARCHS}")
+      if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
+        set_source_files_properties(${MARLIN_MOE_SM75_SRC}
+          PROPERTIES COMPILE_FLAGS "-static-global-template-stub=false")
+      endif()
+      list(APPEND VLLM_MOE_EXT_SRC ${MARLIN_MOE_SM75_SRC})
+    endif()
 
     if (MARLIN_MOE_FP8_ARCHS)
       file(GLOB MARLIN_MOE_FP8_SRC "csrc/moe/marlin_moe_wna16/sm89_kernel_*.cu")
@@ -1050,7 +1085,17 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
       list(APPEND VLLM_MOE_EXT_SRC ${MARLIN_MOE_FP8_SRC})
     endif()
 
-    message(STATUS "Building Marlin MOE kernels for archs: ${MARLIN_MOE_ARCHS}")
+    set(MARLIN_MOE_OTHER_SRC "csrc/moe/marlin_moe_wna16/ops.cu")
+    set_gencode_flags_for_srcs(
+      SRCS "${MARLIN_MOE_OTHER_SRC}"
+      CUDA_ARCHS "${MARLIN_MOE_OTHER_ARCHS}")
+    if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
+      set_source_files_properties(${MARLIN_MOE_OTHER_SRC}
+        PROPERTIES COMPILE_FLAGS "-static-global-template-stub=false")
+    endif()
+    list(APPEND VLLM_MOE_EXT_SRC "${MARLIN_MOE_OTHER_SRC}")
+
+    message(STATUS "Building Marlin MOE kernels for archs: ${MARLIN_MOE_OTHER_ARCHS}")
   else()
     message(STATUS "Not building Marlin MOE kernels as no compatible archs found"
                    " in CUDA target architectures")

benchmarks/kernels/benchmark_activation.py

@@ -13,8 +13,8 @@ from vllm.triton_utils import triton
 from vllm.utils.argparse_utils import FlexibleArgumentParser
 from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE
 
-batch_size_range = [1, 16, 32, 64, 128]
-seq_len_range = [1, 16, 64, 128, 256, 512, 1024, 2048, 4096]
+batch_size_range = [1, 16, 128]
+seq_len_range = [1, 16, 64, 1024, 4096]
 intermediate_size = [3072, 9728, 12288]
 configs = list(itertools.product(batch_size_range, seq_len_range, intermediate_size))
 

cmake/cpu_extension.cmake

@@ -330,7 +330,7 @@ if ((AVX512_FOUND AND NOT AVX512_DISABLED) OR (ASIMD_FOUND AND NOT APPLE_SILICON
         PUBLIC ${oneDNN_BINARY_DIR}/include
         PRIVATE ${oneDNN_SOURCE_DIR}/src
     )
-    target_link_libraries(dnnl_ext dnnl)
+    target_link_libraries(dnnl_ext dnnl torch)
     target_compile_options(dnnl_ext PRIVATE ${CXX_COMPILE_FLAGS} -fPIC)
     list(APPEND LIBS dnnl_ext)
     set(USE_ONEDNN ON)
@@ -358,13 +358,13 @@ set(VLLM_EXT_SRC
     "csrc/cpu/pos_encoding.cpp"
     "csrc/moe/dynamic_4bit_int_moe_cpu.cpp"
     "csrc/cpu/cpu_attn.cpp"
-    "csrc/cpu/scratchpad_manager.cpp"
     "csrc/cpu/torch_bindings.cpp")
 
 if (AVX512_FOUND AND NOT AVX512_DISABLED)
     set(VLLM_EXT_SRC
         "csrc/cpu/shm.cpp"
         "csrc/cpu/cpu_wna16.cpp"
+        "csrc/cpu/cpu_fused_moe.cpp"
         ${VLLM_EXT_SRC})
     if (ENABLE_AVX512BF16 AND ENABLE_AVX512VNNI)
         set(VLLM_EXT_SRC

cmake/external_projects/flashmla.cmake

@@ -35,16 +35,21 @@ message(STATUS "FlashMLA is available at ${flashmla_SOURCE_DIR}")
 # sm90a
 
 set(SUPPORT_ARCHS)
-if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER 12.3)
-    list(APPEND SUPPORT_ARCHS 9.0a)
+if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.3)
+    list(APPEND SUPPORT_ARCHS "9.0a")
 endif()
-if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER 12.8)
-    list(APPEND SUPPORT_ARCHS 10.0a)
+if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.9)
+    # CUDA 12.9 has introduced "Family-Specific Architecture Features"
+    # this supports all compute_10x family
+    list(APPEND SUPPORT_ARCHS "10.0f")
+elseif(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
+    list(APPEND SUPPORT_ARCHS "10.0a")
 endif()
 
 
 cuda_archs_loose_intersection(FLASH_MLA_ARCHS "${SUPPORT_ARCHS}" "${CUDA_ARCHS}")
 if(FLASH_MLA_ARCHS)
+    message(STATUS "FlashMLA CUDA architectures: ${FLASH_MLA_ARCHS}")
     set(VLLM_FLASHMLA_GPU_FLAGS ${VLLM_GPU_FLAGS})
     list(APPEND VLLM_FLASHMLA_GPU_FLAGS "--expt-relaxed-constexpr" "--expt-extended-lambda" "--use_fast_math")
 
@@ -126,7 +131,8 @@ if(FLASH_MLA_ARCHS)
         $<$<COMPILE_LANGUAGE:CUDA>:-UPy_LIMITED_API>
         $<$<COMPILE_LANGUAGE:CXX>:-UPy_LIMITED_API>)
 else()
-    # Create empty targets for setup.py when not targeting sm90a systems
+    message(STATUS "FlashMLA will not compile: unsupported CUDA architecture ${CUDA_ARCHS}")
+    # Create empty targets for setup.py on unsupported systems
     add_custom_target(_flashmla_C)
     add_custom_target(_flashmla_extension_C)
 endif()