[Quant] Support MXFP4 W4A16 for compressed-tensors MoE models

.buildkite/lm-eval-harness/test_lm_eval_correctness.py

@@ -60,6 +60,7 @@ def launch_lm_eval(eval_config, tp_size):
         f"add_bos_token=true,"
         f"trust_remote_code={trust_remote_code},"
         f"max_model_len={max_model_len},"
+        "allow_deprecated_quantization=True,"
     )
 
     env_vars = eval_config.get("env_vars", None)

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

@@ -209,12 +209,21 @@ if [[ $commands == *"--shard-id="* ]]; then
     wait "${pid}"
     STATUS+=($?)
   done
+  at_least_one_shard_with_tests=0
   for st in "${STATUS[@]}"; do
-    if [[ ${st} -ne 0 ]]; then
+    if [[ ${st} -ne 0 ]] && [[ ${st} -ne 5 ]]; then
       echo "One of the processes failed with $st"
       exit "${st}"
+    elif [[ ${st} -eq 5 ]]; then
+      echo "Shard exited with status 5 (no tests collected) - treating as success"
+    else # This means st is 0
+      at_least_one_shard_with_tests=1
     fi
   done
+  if [[ ${#STATUS[@]} -gt 0 && ${at_least_one_shard_with_tests} -eq 0 ]]; then
+    echo "All shards reported no tests collected. Failing the build."
+    exit 1
+  fi
 else
   echo "Render devices: $BUILDKITE_AGENT_META_DATA_RENDER_DEVICES"
   docker run \

.buildkite/test-amd.yaml

@@ -162,8 +162,7 @@ steps:
   - tests/entrypoints/test_chat_utils
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - 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/ --ignore=entrypoints/openai/test_vision_embeds.py
-  - pytest -v -s entrypoints/openai/test_vision_embeds.py
+  - 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/ --ignore=entrypoints/openai/responses
   - pytest -v -s entrypoints/test_chat_utils.py
 
 - label: Entrypoints Integration Test (API Server 2)
@@ -200,6 +199,21 @@ steps:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
   - pytest -v -s entrypoints/pooling
 
+- label: Entrypoints Integration Test (Responses API)
+  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/openai/responses
+  commands:
+  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+  - pytest -v -s entrypoints/openai/responses
+
 - label: Distributed Tests (4 GPUs) # 35min
   timeout_in_minutes: 50
   mirror_hardwares: [amdexperimental]
@@ -731,7 +745,7 @@ steps:
 
 - label: Quantization Test # 70min
   timeout_in_minutes: 90
-  mirror_hardwares: [amdexperimental]
+  mirror_hardwares: [amdexperimental, amdproduction]
   agent_pool: mi325_1
   # grade: Blocking
   source_file_dependencies:
@@ -856,7 +870,7 @@ steps:
 - label: Language Models Tests (Extra Standard) %N
   timeout_in_minutes: 45
   mirror_hardwares: [amdexperimental]
-  agent_pool: mi325_2
+  agent_pool: mi325_8
   # grade: Blocking
   torch_nightly: true
   source_file_dependencies:
@@ -1105,8 +1119,8 @@ steps:
   - vllm/v1/attention/backends/flashinfer.py
   - vllm/v1/attention/backends/mla/cutlass_mla.py
   - vllm/v1/attention/backends/mla/flashinfer_mla.py
+  - vllm/v1/attention/selector.py
   - vllm/platforms/cuda.py
-  - vllm/attention/selector.py
   commands:
     - nvidia-smi
     - python3 examples/offline_inference/basic/chat.py

.buildkite/test-pipeline.yaml

@@ -144,7 +144,7 @@ steps:
   - tests/entrypoints/test_chat_utils
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - 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/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/ --ignore=entrypoints/openai/responses
   - pytest -v -s entrypoints/test_chat_utils.py
 
 - label: Entrypoints Integration Test (API Server 2)
@@ -177,6 +177,18 @@ steps:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
   - pytest -v -s entrypoints/pooling
 
+- label: Entrypoints Integration Test (Responses API)
+  timeout_in_minutes: 50
+  mirror_hardwares: [amdexperimental]
+  working_dir: "/vllm-workspace/tests"
+  fast_check: true
+  torch_nightly: true
+  source_file_dependencies:
+  - vllm/
+  - tests/entrypoints/openai/responses
+  commands:
+  - pytest -v -s entrypoints/openai/responses
+
 - label: Distributed Tests (4 GPUs) # 35min
   timeout_in_minutes: 50
   mirror_hardwares: [amdexperimental]
@@ -954,8 +966,8 @@ steps:
   - vllm/v1/attention/backends/flashinfer.py
   - vllm/v1/attention/backends/mla/cutlass_mla.py
   - vllm/v1/attention/backends/mla/flashinfer_mla.py
+  - vllm/v1/attention/selector.py
   - vllm/platforms/cuda.py
-  - vllm/attention/selector.py
   commands:
     - nvidia-smi
     - python3 examples/offline_inference/basic/chat.py

.buildkite/test_areas/entrypoints.yaml

@@ -34,10 +34,9 @@ steps:
   - tests/entrypoints/test_chat_utils
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - 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/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/ --ignore=entrypoints/openai/responses
   - pytest -v -s entrypoints/test_chat_utils.py
 
-
 - label: Entrypoints Integration (API Server 2)
   timeout_in_minutes: 130
   working_dir: "/vllm-workspace/tests"
@@ -64,6 +63,14 @@ steps:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
   - pytest -v -s entrypoints/pooling
 
+- label: Entrypoints Integration (Responses API)
+  timeout_in_minutes: 50
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/
+  - tests/entrypoints/openai/responses
+  commands:
+  - pytest -v -s entrypoints/openai/responses
 
 - label: Entrypoints V1
   timeout_in_minutes: 50

.buildkite/test_areas/kernels.yaml

@@ -90,8 +90,8 @@ steps:
   - vllm/v1/attention/backends/flashinfer.py
   - vllm/v1/attention/backends/mla/cutlass_mla.py
   - vllm/v1/attention/backends/mla/flashinfer_mla.py
+  - vllm/v1/attention/selector.py
   - vllm/platforms/cuda.py
-  - vllm/attention/selector.py
   commands:
     - nvidia-smi
     - python3 examples/offline_inference/basic/chat.py

.github/CODEOWNERS

@@ -3,7 +3,6 @@
 
 # This lists cover the "core" components of vLLM that require careful review
 /vllm/attention @LucasWilkinson
-/vllm/attention/backends/abstract.py @WoosukKwon @zhuohan123 @youkaichao @alexm-redhat @njhill
 /vllm/executor/executor_base.py @zhuohan123 @youkaichao @alexm-redhat @njhill @22quinn
 /vllm/model_executor/layers/fused_moe @mgoin @pavanimajety
 /vllm/model_executor/layers/quantization @mgoin @robertgshaw2-redhat @tlrmchlsmth @yewentao256 @pavanimajety
@@ -27,6 +26,7 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
 
 # vLLM V1
 /vllm/v1/attention @LucasWilkinson
+/vllm/v1/attention/backend.py @WoosukKwon @zhuohan123 @youkaichao @alexm-redhat @njhill
 /vllm/v1/attention/backends/mla @pavanimajety
 /vllm/v1/attention/backends/flashinfer.py @mgoin @pavanimajety
 /vllm/v1/attention/backends/triton_attn.py @tdoublep
@@ -117,15 +117,15 @@ mkdocs.yaml @hmellor
 /vllm/transformers_utils/tokenizers/mistral.py @patrickvonplaten
 
 # Kernels
-/vllm/attention/ops/chunked_prefill_paged_decode.py @tdoublep
-/vllm/attention/ops/triton_unified_attention.py @tdoublep
+/vllm/v1/attention/ops/chunked_prefill_paged_decode.py @tdoublep
+/vllm/v1/attention/ops/triton_unified_attention.py @tdoublep
 
 # ROCm related: specify owner with write access to notify AMD folks for careful code review
 /vllm/**/*rocm* @tjtanaa
 /docker/Dockerfile.rocm* @gshtras @tjtanaa
 /vllm/v1/attention/backends/rocm*.py @gshtras @tjtanaa
 /vllm/v1/attention/backends/mla/rocm*.py @gshtras @tjtanaa
-/vllm/attention/ops/rocm*.py @gshtras @tjtanaa
+/vllm/v1/attention/ops/rocm*.py @gshtras @tjtanaa
 /vllm/model_executor/layers/fused_moe/rocm*.py @gshtras @tjtanaa
 /csrc/rocm @gshtras @tjtanaa
 /requirements/*rocm* @tjtanaa

.github/mergify.yml

@@ -222,10 +222,10 @@ pull_request_rules:
       - files~=^csrc/rocm/
       - files~=^docker/Dockerfile.rocm
       - files~=^requirements/rocm.*\.txt
-      - files~=^vllm/attention/backends/rocm.*\.py
-      - files~=^vllm/attention/ops/rocm.*\.py
       - files~=^vllm/model_executor/layers/fused_moe/rocm.*\.py
+      - files~=^vllm/v1/attention/backends/rocm.*\.py
       - files~=^vllm/v1/attention/backends/mla/rocm.*\.py
+      - files~=^vllm/v1/attention/ops/rocm.*\.py
       - files~=^tests/kernels/.*_rocm.*\.py
       - files=vllm/platforms/rocm.py
       - title~=(?i)AMD

CMakeLists.txt

@@ -282,6 +282,7 @@ endif()
 set(VLLM_EXT_SRC
   "csrc/mamba/mamba_ssm/selective_scan_fwd.cu"
   "csrc/cache_kernels.cu"
+  "csrc/cache_kernels_fused.cu"
   "csrc/attention/paged_attention_v1.cu"
   "csrc/attention/paged_attention_v2.cu"
   "csrc/attention/merge_attn_states.cu"

benchmarks/kernels/benchmark_reshape_and_cache_flash.py

@@ -7,16 +7,16 @@
 from tabulate import tabulate
 
 from vllm import _custom_ops as ops
-from vllm.attention.ops.triton_reshape_and_cache_flash import (
-    triton_reshape_and_cache_flash,
-)
 from vllm.logger import init_logger
 from vllm.utils.argparse_utils import FlexibleArgumentParser
 from vllm.utils.torch_utils import (
     STR_DTYPE_TO_TORCH_DTYPE,
     create_kv_caches_with_random_flash,
     set_random_seed,
 )
+from vllm.v1.attention.ops.triton_reshape_and_cache_flash import (
+    triton_reshape_and_cache_flash,
+)
 
 logger = init_logger(__name__)