Merge tag 'v0.14.0' into v0.14.0-dev

.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
@@ -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

.gitignore

@@ -227,3 +227,8 @@ ep_kernels_workspace/
 
 # Allow tracked library source folders under submodules (e.g., benchmarks/lib)
 !vllm/benchmarks/lib/
+
+# Generated gRPC protobuf files (compiled at build time from vllm_engine.proto)
+vllm/grpc/vllm_engine_pb2.py
+vllm/grpc/vllm_engine_pb2_grpc.py
+vllm/grpc/vllm_engine_pb2.pyi

CMakeLists.txt

@@ -287,6 +287,7 @@ 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"
@@ -365,6 +366,8 @@ 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" "${CUDA_ARCHS}")
   # marlin arches for fp8 input
@@ -372,8 +375,10 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
   # - sm90 and sm100 don't support QMMA.16832.F32.E4M3.E4M3 SAAS instruction
   # so we only enable fp8 computation for SM89 (e.g. RTX 40x0)  and 12.0 (e.g. RTX 50x0)
   cuda_archs_loose_intersection(MARLIN_FP8_ARCHS "8.9;12.0" "${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
@@ -414,25 +419,39 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
       message(STATUS "Marlin generation script has not changed, skipping generation.")
     endif()
 
-    file(GLOB MARLIN_TEMPLATE_KERNEL_SRC "csrc/quantization/gptq_marlin/sm80_kernel_*_float16.cu")
-    set_gencode_flags_for_srcs(
-      SRCS "${MARLIN_TEMPLATE_KERNEL_SRC}"
-      CUDA_ARCHS "${MARLIN_ARCHS}")
-    if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
-      set_source_files_properties(${MARLIN_TEMPLATE_KERNEL_SRC}
-        PROPERTIES COMPILE_FLAGS "-static-global-template-stub=false")
+    if (MARLIN_ARCHS)
+      file(GLOB MARLIN_TEMPLATE_KERNEL_SRC "csrc/quantization/gptq_marlin/sm80_kernel_*_float16.cu")
+      set_gencode_flags_for_srcs(
+        SRCS "${MARLIN_TEMPLATE_KERNEL_SRC}"
+        CUDA_ARCHS "${MARLIN_ARCHS}")
+      if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
+        set_source_files_properties(${MARLIN_TEMPLATE_KERNEL_SRC}
+          PROPERTIES COMPILE_FLAGS "-static-global-template-stub=false")
+      endif()
+      list(APPEND VLLM_EXT_SRC ${MARLIN_TEMPLATE_KERNEL_SRC})
+
+      file(GLOB MARLIN_TEMPLATE_BF16_KERNEL_SRC "csrc/quantization/gptq_marlin/sm80_kernel_*_bfloat16.cu")
+      set_gencode_flags_for_srcs(
+        SRCS "${MARLIN_TEMPLATE_BF16_KERNEL_SRC}"
+        CUDA_ARCHS "${MARLIN_BF16_ARCHS}")
+      if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
+        set_source_files_properties(${MARLIN_TEMPLATE_BF16_KERNEL_SRC}
+          PROPERTIES COMPILE_FLAGS "-static-global-template-stub=false")
+      endif()
+      list(APPEND VLLM_EXT_SRC ${MARLIN_TEMPLATE_BF16_KERNEL_SRC})
     endif()
-    list(APPEND VLLM_EXT_SRC ${MARLIN_TEMPLATE_KERNEL_SRC})
 
-    file(GLOB MARLIN_TEMPLATE_BF16_KERNEL_SRC "csrc/quantization/gptq_marlin/sm80_kernel_*_bfloat16.cu")
-    set_gencode_flags_for_srcs(
-      SRCS "${MARLIN_TEMPLATE_BF16_KERNEL_SRC}"
-      CUDA_ARCHS "${MARLIN_BF16_ARCHS}")
-    if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
-      set_source_files_properties(${MARLIN_TEMPLATE_BF16_KERNEL_SRC}
-        PROPERTIES COMPILE_FLAGS "-static-global-template-stub=false")
+    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()
-    list(APPEND VLLM_EXT_SRC ${MARLIN_TEMPLATE_BF16_KERNEL_SRC})
 
     if (MARLIN_FP8_ARCHS) 
       file(GLOB MARLIN_TEMPLATE_FP8_KERNEL_SRC "csrc/quantization/gptq_marlin/sm89_kernel_*.cu")
@@ -454,14 +473,14 @@ 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: ${MARLIN_OTHER_ARCHS}")
   else()
     message(STATUS "Not building Marlin kernels as no compatible archs found"
                    " in CUDA target architectures")
@@ -789,24 +808,6 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
   else()
     cuda_archs_loose_intersection(SCALED_MM_ARCHS "10.0a;10.1a;10.3a" "${CUDA_ARCHS}")
   endif()
-  if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8 AND SCALED_MM_ARCHS)
-    set(SRCS "csrc/quantization/w8a8/cutlass/moe/blockwise_scaled_group_mm_sm100.cu")
-    set_gencode_flags_for_srcs(
-      SRCS "${SRCS}"
-      CUDA_ARCHS "${SCALED_MM_ARCHS}")
-    list(APPEND VLLM_EXT_SRC "${SRCS}")
-    list(APPEND VLLM_GPU_FLAGS "-DENABLE_CUTLASS_MOE_SM100=1")
-    message(STATUS "Building blockwise_scaled_group_mm_sm100 for archs: ${SCALED_MM_ARCHS}")
-  else()
-    if (NOT ${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8 AND SCALED_MM_ARCHS)
-      message(STATUS "Not building blockwise_scaled_group_mm_sm100 kernels as CUDA Compiler version is "
-                     "not >= 12.8, we recommend upgrading to CUDA 12.8 or later "
-                     "if you intend on running FP8 quantized MoE models on Blackwell.")
-    else()
-      message(STATUS "Not building blockwise_scaled_group_mm_sm100 as no compatible archs found "
-                     "in CUDA target architectures")
-    endif()
-  endif()
 
   #
   # Machete kernels
@@ -989,12 +990,16 @@ 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
@@ -1035,16 +1040,29 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
       message(STATUS "Marlin MOE generation script has not changed, skipping generation.")
     endif()
 
-    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}")
-    if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
-      set_source_files_properties(${MARLIN_MOE_SRC}
-        PROPERTIES COMPILE_FLAGS "-static-global-template-stub=false")
+    if (MARLIN_MOE_ARCHS)
+      file(GLOB MARLIN_MOE_SRC "csrc/moe/marlin_moe_wna16/sm80_kernel_*.cu")
+      set_gencode_flags_for_srcs(
+        SRCS "${MARLIN_MOE_SRC}"
+        CUDA_ARCHS "${MARLIN_MOE_ARCHS}")
+      if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
+        set_source_files_properties(${MARLIN_MOE_SRC}
+          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()
-    list(APPEND VLLM_MOE_EXT_SRC ${MARLIN_MOE_SRC})
 
     if (MARLIN_MOE_FP8_ARCHS)
       file(GLOB MARLIN_MOE_FP8_SRC "csrc/moe/marlin_moe_wna16/sm89_kernel_*.cu")
@@ -1058,7 +1076,17 @@ 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")

README_ORIGIN.md

@@ -14,51 +14,8 @@ Easy, fast, and cheap LLM serving for everyone
 | <a href="https://docs.vllm.ai"><b>Documentation</b></a> | <a href="https://blog.vllm.ai/"><b>Blog</b></a> | <a href="https://arxiv.org/abs/2309.06180"><b>Paper</b></a> | <a href="https://x.com/vllm_project"><b>Twitter/X</b></a> | <a href="https://discuss.vllm.ai"><b>User Forum</b></a> | <a href="https://slack.vllm.ai"><b>Developer Slack</b></a> |
 </p>
 
----
-Join us at the [PyTorch Conference, October 22-23](https://events.linuxfoundation.org/pytorch-conference/) and [Ray Summit, November 3-5](https://www.anyscale.com/ray-summit/2025) in San Francisco for our latest updates on vLLM and to meet the vLLM team! Register now for the largest vLLM community events of the year!
-
----
-
-*Latest News* 🔥
-
-- [2025/11] We hosted [vLLM Bangkok Meetup](https://luma.com/v0f647nv). We explored vLLM and LMCache inference and low-resource language adaptation with speakers from Embedded LLM, AMD, and Red Hat. Please find the meetup slides [here](https://drive.google.com/drive/folders/1H0DS57F8HQ5q3kSOSoRmucPJWL3E0A_X?usp=sharing).
-- [2025/11] We hosted [the first vLLM Europe Meetup in Zurich](https://luma.com/0gls27kb) focused on quantization, distributed inference, and reinforcement learning at scale with speakers from Mistral, IBM, and Red Hat. Please find the meetup slides [here](https://docs.google.com/presentation/d/1UC9PTLCHYXQpOmJDSFg6Sljra3iVXzc09DeEI7dnxMc/edit?usp=sharing) and recording [here](https://www.youtube.com/watch?v=6m6ZE6yVEDI)
-- [2025/11] We hosted [vLLM Beijing Meetup](https://mp.weixin.qq.com/s/xSrYXjNgr1HbCP4ExYNG1w) focusing on distributed inference and diverse accelerator support with vLLM! Please find the meetup slides [here](https://drive.google.com/drive/folders/1nQJ8ZkLSjKxvu36sSHaceVXtttbLvvu-?usp=drive_link).
-- [2025/10] We hosted [vLLM Shanghai Meetup](https://mp.weixin.qq.com/s/__xb4OyOsImz-9eAVrdlcg) focused on hands-on vLLM inference optimization! Please find the meetup slides [here](https://drive.google.com/drive/folders/1KqwjsFJLfEsC8wlDugnrR61zsWHt94Q6).
-- [2025/09] We hosted [vLLM Toronto Meetup](https://luma.com/e80e0ymm) focused on tackling inference at scale and speculative decoding with speakers from NVIDIA and Red Hat! Please find the meetup slides [here](https://docs.google.com/presentation/d/1IYJYmJcu9fLpID5N5RbW_vO0XLo0CGOR14IXOjB61V8/edit?usp=sharing).
-- [2025/08] We hosted [vLLM Shenzhen Meetup](https://mp.weixin.qq.com/s/k8ZBO1u2_2odgiKWH_GVTQ) focusing on the ecosystem around vLLM! Please find the meetup slides [here](https://drive.google.com/drive/folders/1Ua2SVKVSu-wp5vou_6ElraDt2bnKhiEA).
-- [2025/08] We hosted [vLLM Singapore Meetup](https://www.sginnovate.com/event/vllm-sg-meet). We shared V1 updates, disaggregated serving and MLLM speedups with speakers from Embedded LLM, AMD, WekaIO, and A*STAR. Please find the meetup slides [here](https://drive.google.com/drive/folders/1ncf3GyqLdqFaB6IeB834E5TZJPLAOiXZ?usp=sharing).
-- [2025/08] We hosted [vLLM Shanghai Meetup](https://mp.weixin.qq.com/s/pDmAXHcN7Iqc8sUKgJgGtg) focusing on building, developing, and integrating with vLLM! Please find the meetup slides [here](https://drive.google.com/drive/folders/1OvLx39wnCGy_WKq8SiVKf7YcxxYI3WCH).
-- [2025/05] vLLM is now a hosted project under PyTorch Foundation! Please find the announcement [here](https://pytorch.org/blog/pytorch-foundation-welcomes-vllm/).
-- [2025/01] We are excited to announce the alpha release of vLLM V1: A major architectural upgrade with 1.7x speedup! Clean code, optimized execution loop, zero-overhead prefix caching, enhanced multimodal support, and more. Please check out our blog post [here](https://blog.vllm.ai/2025/01/27/v1-alpha-release.html).
-
-<details>
-<summary>Previous News</summary>
-
-- [2025/08] We hosted [vLLM Korea Meetup](https://luma.com/cgcgprmh) with Red Hat and Rebellions! We shared the latest advancements in vLLM along with project spotlights from the vLLM Korea community. Please find the meetup slides [here](https://drive.google.com/file/d/1bcrrAE1rxUgx0mjIeOWT6hNe2RefC5Hm/view).
-- [2025/08] We hosted [vLLM Beijing Meetup](https://mp.weixin.qq.com/s/dgkWg1WFpWGO2jCdTqQHxA) focusing on large-scale LLM deployment! Please find the meetup slides [here](https://drive.google.com/drive/folders/1Pid6NSFLU43DZRi0EaTcPgXsAzDvbBqF) and the recording [here](https://www.chaspark.com/#/live/1166916873711665152).
-- [2025/05] We hosted [NYC vLLM Meetup](https://lu.ma/c1rqyf1f)! Please find the meetup slides [here](https://docs.google.com/presentation/d/1_q_aW_ioMJWUImf1s1YM-ZhjXz8cUeL0IJvaquOYBeA/edit?usp=sharing).
-- [2025/04] We hosted [Asia Developer Day](https://www.sginnovate.com/event/limited-availability-morning-evening-slots-remaining-inaugural-vllm-asia-developer-day)! Please find the meetup slides from the vLLM team [here](https://docs.google.com/presentation/d/19cp6Qu8u48ihB91A064XfaXruNYiBOUKrBxAmDOllOo/edit?usp=sharing).
-- [2025/03] We hosted [vLLM x Ollama Inference Night](https://lu.ma/vllm-ollama)! Please find the meetup slides from the vLLM team [here](https://docs.google.com/presentation/d/16T2PDD1YwRnZ4Tu8Q5r6n53c5Lr5c73UV9Vd2_eBo4U/edit?usp=sharing).
-- [2025/03] We hosted [the first vLLM China Meetup](https://mp.weixin.qq.com/s/n77GibL2corAtQHtVEAzfg)! Please find the meetup slides from vLLM team [here](https://docs.google.com/presentation/d/1REHvfQMKGnvz6p3Fd23HhSO4c8j5WPGZV0bKYLwnHyQ/edit?usp=sharing).
-- [2025/03] We hosted [the East Coast vLLM Meetup](https://lu.ma/7mu4k4xx)! Please find the meetup slides [here](https://docs.google.com/presentation/d/1NHiv8EUFF1NLd3fEYODm56nDmL26lEeXCaDgyDlTsRs/edit#slide=id.g31441846c39_0_0).
-- [2025/02] We hosted [the ninth vLLM meetup](https://lu.ma/h7g3kuj9) with Meta! Please find the meetup slides from vLLM team [here](https://docs.google.com/presentation/d/1jzC_PZVXrVNSFVCW-V4cFXb6pn7zZ2CyP_Flwo05aqg/edit?usp=sharing) and AMD [here](https://drive.google.com/file/d/1Zk5qEJIkTmlQ2eQcXQZlljAx3m9s7nwn/view?usp=sharing). The slides from Meta will not be posted.
-- [2025/01] We hosted [the eighth vLLM meetup](https://lu.ma/zep56hui) with Google Cloud! Please find the meetup slides from vLLM team [here](https://docs.google.com/presentation/d/1epVkt4Zu8Jz_S5OhEHPc798emsYh2BwYfRuDDVEF7u4/edit?usp=sharing), and Google Cloud team [here](https://drive.google.com/file/d/1h24pHewANyRL11xy5dXUbvRC9F9Kkjix/view?usp=sharing).
-- [2024/12] vLLM joins [pytorch ecosystem](https://pytorch.org/blog/vllm-joins-pytorch)! Easy, Fast, and Cheap LLM Serving for Everyone!
-- [2024/11] We hosted [the seventh vLLM meetup](https://lu.ma/h0qvrajz) with Snowflake! Please find the meetup slides from vLLM team [here](https://docs.google.com/presentation/d/1e3CxQBV3JsfGp30SwyvS3eM_tW-ghOhJ9PAJGK6KR54/edit?usp=sharing), and Snowflake team [here](https://docs.google.com/presentation/d/1qF3RkDAbOULwz9WK5TOltt2fE9t6uIc_hVNLFAaQX6A/edit?usp=sharing).
-- [2024/10] We have just created a developer slack ([slack.vllm.ai](https://slack.vllm.ai)) focusing on coordinating contributions and discussing features. Please feel free to join us there!
-- [2024/10] Ray Summit 2024 held a special track for vLLM! Please find the opening talk slides from the vLLM team [here](https://docs.google.com/presentation/d/1B_KQxpHBTRa_mDF-tR6i8rWdOU5QoTZNcEg2MKZxEHM/edit?usp=sharing). Learn more from the [talks](https://www.youtube.com/playlist?list=PLzTswPQNepXl6AQwifuwUImLPFRVpksjR) from other vLLM contributors and users!
-- [2024/09] We hosted [the sixth vLLM meetup](https://lu.ma/87q3nvnh) with NVIDIA! Please find the meetup slides [here](https://docs.google.com/presentation/d/1wrLGwytQfaOTd5wCGSPNhoaW3nq0E-9wqyP7ny93xRs/edit?usp=sharing).
-- [2024/07] We hosted [the fifth vLLM meetup](https://lu.ma/lp0gyjqr) with AWS! Please find the meetup slides [here](https://docs.google.com/presentation/d/1RgUD8aCfcHocghoP3zmXzck9vX3RCI9yfUAB2Bbcl4Y/edit?usp=sharing).
-- [2024/07] In partnership with Meta, vLLM officially supports Llama 3.1 with FP8 quantization and pipeline parallelism! Please check out our blog post [here](https://blog.vllm.ai/2024/07/23/llama31.html).
-- [2024/06] We hosted [the fourth vLLM meetup](https://lu.ma/agivllm) with Cloudflare and BentoML! Please find the meetup slides [here](https://docs.google.com/presentation/d/1iJ8o7V2bQEi0BFEljLTwc5G1S10_Rhv3beed5oB0NJ4/edit?usp=sharing).
-- [2024/04] We hosted [the third vLLM meetup](https://robloxandvllmmeetup2024.splashthat.com/) with Roblox! Please find the meetup slides [here](https://docs.google.com/presentation/d/1A--47JAK4BJ39t954HyTkvtfwn0fkqtsL8NGFuslReM/edit?usp=sharing).
-- [2024/01] We hosted [the second vLLM meetup](https://lu.ma/ygxbpzhl) with IBM! Please find the meetup slides [here](https://docs.google.com/presentation/d/12mI2sKABnUw5RBWXDYY-HtHth4iMSNcEoQ10jDQbxgA/edit?usp=sharing).
-- [2023/10] We hosted [the first vLLM meetup](https://lu.ma/first-vllm-meetup) with a16z! Please find the meetup slides [here](https://docs.google.com/presentation/d/1QL-XPFXiFpDBh86DbEegFXBXFXjix4v032GhShbKf3s/edit?usp=sharing).
-- [2023/08] We would like to express our sincere gratitude to [Andreessen Horowitz](https://a16z.com/2023/08/30/supporting-the-open-source-ai-community/) (a16z) for providing a generous grant to support the open-source development and research of vLLM.
-- [2023/06] We officially released vLLM! FastChat-vLLM integration has powered [LMSYS Vicuna and Chatbot Arena](https://chat.lmsys.org) since mid-April. Check out our [blog post](https://vllm.ai).
-
-</details>
+🔥 We have built a vllm website to help you get started with vllm. Please visit [vllm.ai](https://vllm.ai) to learn more.
+For events, please visit [vllm.ai/events](https://vllm.ai/events) to join us.
 
 ---
 
@@ -118,50 +75,6 @@ Visit our [documentation](https://docs.vllm.ai/en/latest/) to learn more.
 We welcome and value any contributions and collaborations.
 Please check out [Contributing to vLLM](https://docs.vllm.ai/en/latest/contributing/index.html) for how to get involved.
 
-## Sponsors
-
-vLLM is a community project. Our compute resources for development and testing are supported by the following organizations. Thank you for your support!
-
-<!-- Note: Please sort them in alphabetical order. -->
-<!-- Note: Please keep these consistent with docs/community/sponsors.md -->
-Cash Donations:
-
-- a16z
-- Dropbox
-- Sequoia Capital
-- Skywork AI
-- ZhenFund
-
-Compute Resources:
-
-- Alibaba Cloud
-- AMD
-- Anyscale
-- Arm
-- AWS
-- Crusoe Cloud
-- Databricks
-- DeepInfra
-- Google Cloud
-- IBM
-- Intel
-- Lambda Lab
-- Nebius
-- Novita AI
-- NVIDIA
-- Red Hat
-- Replicate
-- Roblox
-- RunPod
-- Trainy
-- UC Berkeley
-- UC San Diego
-- Volcengine
-
-Slack Sponsor: Anyscale
-
-We also have an official fundraising venue through [OpenCollective](https://opencollective.com/vllm). We plan to use the fund to support the development, maintenance, and adoption of vLLM.
-
 ## Citation
 
 If you use vLLM for your research, please cite our [paper](https://arxiv.org/abs/2309.06180):
@@ -182,7 +95,7 @@ If you use vLLM for your research, please cite our [paper](https://arxiv.org/abs
 - For discussing with fellow users, please use the [vLLM Forum](https://discuss.vllm.ai)
 - For coordinating contributions and development, please use [Slack](https://slack.vllm.ai)
 - For security disclosures, please use GitHub's [Security Advisories](https://github.com/vllm-project/vllm/security/advisories) feature
-- For collaborations and partnerships, please contact us at [vllm-questions@lists.berkeley.edu](mailto:vllm-questions@lists.berkeley.edu)
+- For collaborations and partnerships, please contact us at [collaboration@vllm.ai](mailto:collaboration@vllm.ai)
 <!-- --8<-- [end:contact-us] -->
 
 ## Media Kit

RELEASE.md

 # Releasing vLLM
 
-vLLM releases offer a reliable version of the code base, packaged into a binary format that can be conveniently accessed via PyPI. These releases also serve as key milestones for the development team to communicate with the community about newly available features, improvements, and upcoming changes that could affect users, including potential breaking changes.
+vLLM releases offer a reliable version of the code base, packaged into a binary format that can be conveniently accessed via [PyPI](https://pypi.org/project/vllm). These releases also serve as key milestones for the development team to communicate with the community about newly available features, improvements, and upcoming changes that could affect users, including potential breaking changes.
 
-## Release Versioning
+## Release Cadence and Versioning
 
-vLLM uses a “right-shifted” versioning scheme where a new patch release is out every 2 weeks. And patch releases contain features and bug fixes (as opposed to semver where patch release contains only backwards-compatible bug fixes). When critical fixes need to be made, special release post1 is released.
+We aim to have a regular release every 2 weeks. Since v0.12.0, regular releases increment the minor version rather than patch version. The list of past releases can be found [here](https://vllm.ai/releases).
 
-* _major_ major architectural milestone and when incompatible API changes are made, similar to PyTorch 2.0.
-* _minor_ major features
-* _patch_ features and backwards-compatible bug fixes
-* _post1_ or _patch-1_ backwards-compatible bug fixes, either explicit or implicit post release
+Our version numbers are expressed in the form `vX.Y.Z`, where `X` is the major version, `Y` is the minor version, and `Z` is the patch version. They are incremented according to the following rules:
 
-## Release Cadence
+* _Major_ releases are reserved for architectural milestones involving sweeping API changes, similar to PyTorch 2.0.
+* _Minor_ releases correspond to regular releases, which include new features, bug fixes and other backwards-compatible changes.
+* _Patch_ releases correspond to special releases for new models, as well as emergency patches for critical performance, functionality and security issues.
 
-Patch release is released on bi-weekly basis. Post release 1-3 days after patch release and uses same branch as patch release.
-Following is the release cadence for year 2025. All future release dates below are tentative. Please note: Post releases are optional.
+This versioning scheme is similar to [SemVer](https://semver.org/) for compatibility purposes, except that backwards compatibility is only guaranteed for a limited number of minor releases (see our [deprecation policy](https://docs.vllm.ai/en/latest/contributing/deprecation_policy) for details).
 
-| Release Date | Patch release versions | Post Release versions |
-| --- | --- | --- |
-| Jan 2025 | 0.7.0 | --- |
-| Feb 2025 | 0.7.1, 0.7.2, 0.7.3  | --- |
-| Mar 2025 | 0.7.4, 0.7.5 | --- |
-| Apr 2025 | 0.7.6, 0.7.7 | --- |
-| May 2025 | 0.7.8, 0.7.9 | --- |
-| Jun 2025 | 0.7.10, 0.7.11 | --- |
-| Jul 2025 | 0.7.12, 0.7.13 | --- |
-| Aug 2025 | 0.7.14, 0.7.15 | --- |
-| Sep 2025 | 0.7.16, 0.7.17 | --- |
-| Oct 2025 | 0.7.18, 0.7.19 | --- |
-| Nov 2025 | 0.7.20, 0.7.21 | --- |
-| Dec 2025 | 0.7.22, 0.7.23 | --- |
-
-## Release branch
+## Release Branch
 
 Each release is built from a dedicated release branch.
 
-* For _major_, _minor_, _patch_ releases, the release branch cut is performed 1-2 days before release is live.
-* For post releases, previously cut release branch is reused
-* Release builds are triggered via push to RC tag like vX.Y.Z-rc1 . This enables us to build and test multiple RCs for each release.
-* Final tag : vX.Y.Z does not trigger the build but used for Release notes and assets.
-* After branch cut is created we monitor the main branch for any reverts and apply these reverts to a release branch.
+* For _major_ and _minor_ releases, the release branch cut is performed 1-2 days before release is live.
+* For _patch_ releases, previously cut release branch is reused.
+* Release builds are triggered via push to RC tag like `vX.Y.Z-rc1`. This enables us to build and test multiple RCs for each release.
+* Final tag: `vX.Y.Z` does not trigger the build but used for Release notes and assets.
+* After branch cut is created, we monitor the main branch for any reverts and apply these reverts to a release branch.
 
-## Release Cherry-Pick Criteria
+### Cherry-Pick Criteria
 
 After branch cut, we approach finalizing the release branch with clear criteria on what cherry picks are allowed in. Note: a cherry pick is a process to land a PR in the release branch after branch cut. These are typically limited to ensure that the team has sufficient time to complete a thorough round of testing on a stable code base.
 

benchmarks/benchmark_batch_invariance.py

@@ -104,7 +104,6 @@ def run_benchmark_with_batch_invariant(
     random.seed(seed)
 
     # Set environment variables
-    os.environ["VLLM_ATTENTION_BACKEND"] = backend
     if batch_invariant:
         os.environ["VLLM_BATCH_INVARIANT"] = "1"
     else:
@@ -140,6 +139,7 @@ def run_benchmark_with_batch_invariant(
             max_model_len=max_model_len,
             dtype="bfloat16",
             tensor_parallel_size=tp_size,
+            attention_config={"backend": backend},
             enable_prefix_caching=False,
         )
         init_time = time.perf_counter() - start_init

benchmarks/benchmark_ngram_proposer.py

@@ -135,7 +135,6 @@ def benchmark_batched_propose(args):
             block_sizes=[16],
         )
         dummy_input_batch._req_ids = list(str(id) for id in range(args.num_req))
-        dummy_input_batch.spec_decode_unsupported_reqs = ()
         dummy_input_batch.num_tokens_no_spec = [args.num_token] * args.num_req
         dummy_input_batch.token_ids_cpu = np.random.randint(
             0, 20, (args.num_req, args.num_token)
@@ -151,10 +150,8 @@ def benchmark_batched_propose(args):
             start = time.time()
             runner.drafter.propose(
                 sampled_token_ids,
-                dummy_input_batch.req_ids,
                 dummy_input_batch.num_tokens_no_spec,
                 dummy_input_batch.token_ids_cpu,
-                dummy_input_batch.spec_decode_unsupported_reqs,
             )
             end = time.time()
             print(f"Iteration time (s): {end - start}")

benchmarks/cutlass_benchmarks/sparse_benchmarks.py

@@ -343,7 +343,9 @@ def bench(
         return bench_int8(dtype, m, k, n, label, sub_label)
     if dtype == torch.float8_e4m3fn:
         return bench_fp8(dtype, m, k, n, label, sub_label)
-    raise ValueError("unsupported type")
+    raise ValueError(
+        f"Unsupported dtype {dtype}: should be one of torch.int8, torch.float8_e4m3fn."
+    )
 
 
 # runner

benchmarks/kernels/bench_nvfp4_quant.py

+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+import argparse
+import copy
+import itertools
+
+import torch
+from weight_shapes import WEIGHT_SHAPES
+
+from vllm import _custom_ops as ops
+from vllm.platforms import current_platform
+from vllm.scalar_type import scalar_types
+from vllm.triton_utils import triton
+from vllm.utils.flashinfer import flashinfer_fp4_quantize
+
+if not current_platform.has_device_capability(100):
+    raise RuntimeError("NVFP4 requires compute capability of 10.0 (Blackwell)")
+
+FLOAT4_E2M1_MAX = scalar_types.float4_e2m1f.max()
+FLOAT8_E4M3_MAX = torch.finfo(torch.float8_e4m3fn).max
+
+PROVIDER_CFGS = {
+    "vllm": dict(backend="vllm", enabled=True),
+    "flashinfer": dict(backend="flashinfer", enabled=True),
+}
+
+_enabled = [k for k, v in PROVIDER_CFGS.items() if v["enabled"]]
+
+
+def compute_global_scale(tensor: torch.Tensor) -> torch.Tensor:
+    """Compute global scale for FP4 quantization."""
+    amax = torch.abs(tensor).max().to(torch.float32)
+    return FLOAT8_E4M3_MAX * FLOAT4_E2M1_MAX / amax
+
+
+@triton.testing.perf_report(
+    triton.testing.Benchmark(
+        x_names=["batch_size"],
+        x_vals=[1, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096],
+        x_log=False,
+        line_arg="provider",
+        line_vals=_enabled,
+        line_names=_enabled,
+        ylabel="us (lower is better)",
+        plot_name="NVFP4 Input Quantization Latency (us)",
+        args={},
+    )
+)
+def benchmark(batch_size, provider, N, K):
+    M = batch_size
+    device = "cuda"
+    dtype = torch.bfloat16
+
+    # Create input tensor
+    a = torch.randn((M, K), device=device, dtype=dtype)
+
+    # Compute global scale for activation
+    a_global_scale = compute_global_scale(a)
+
+    quantiles = [0.5, 0.2, 0.8]
+
+    cfg = PROVIDER_CFGS[provider]
+
+    if cfg["backend"] == "vllm":
+        # vLLM's FP4 quantization
+        ms, min_ms, max_ms = triton.testing.do_bench_cudagraph(
+            lambda: ops.scaled_fp4_quant(a, a_global_scale),
+            quantiles=quantiles,
+        )
+    elif cfg["backend"] == "flashinfer":
+        # FlashInfer's FP4 quantization
+        # Use is_sf_swizzled_layout=True to match vLLM's output format
+        ms, min_ms, max_ms = triton.testing.do_bench_cudagraph(
+            lambda: flashinfer_fp4_quantize(
+                a, a_global_scale, is_sf_swizzled_layout=True
+            ),
+            quantiles=quantiles,
+        )
+
+    # Convert ms to us for better readability at small batch sizes
+    to_us = lambda t_ms: t_ms * 1000
+    return to_us(ms), to_us(max_ms), to_us(min_ms)
+
+
+def prepare_shapes(args):
+    out = []
+    for model, tp_size in itertools.product(args.models, args.tp_sizes):
+        for KN, tp_dim in copy.deepcopy(WEIGHT_SHAPES[model]):
+            KN[tp_dim] //= tp_size
+            KN.append(model)
+            out.append(KN)
+    return out
+
+
+def _test_accuracy_once(M: int, K: int, dtype: torch.dtype, device: str):
+    """Test accuracy between vLLM and FlashInfer FP4 quantization."""
+    # Create input tensor
+    a = torch.randn((M, K), device=device, dtype=dtype)
+
+    # Compute global scale
+    a_global_scale = compute_global_scale(a)
+
+    # vLLM quantization
+    vllm_fp4, vllm_scale = ops.scaled_fp4_quant(a, a_global_scale)
+
+    # FlashInfer quantization (with swizzled layout to match vLLM's output)
+    flashinfer_fp4, flashinfer_scale = flashinfer_fp4_quantize(
+        a, a_global_scale, is_sf_swizzled_layout=True
+    )
+    flashinfer_scale = flashinfer_scale.view(torch.float8_e4m3fn)
+
+    # Compare outputs
+    torch.testing.assert_close(
+        vllm_fp4,
+        flashinfer_fp4,
+    )
+    print(f"M={M}, K={K}, dtype={dtype}: PASSED")
+
+
+def test_accuracy():
+    """Run accuracy tests across various shapes."""
+    print("\n" + "=" * 60)
+    print("Running accuracy tests: vLLM vs FlashInfer")
+    print("=" * 60)
+
+    device = "cuda"
+    dtype = torch.bfloat16
+
+    # Test various batch sizes and hidden dimensions
+    Ms = [1, 1024]
+    Ks = [4096]
+
+    for M in Ms:
+        for K in Ks:
+            _test_accuracy_once(M, K, dtype, device)
+
+    print("\nAll accuracy tests passed!")
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="Benchmark NVFP4 quantization: vLLM vs FlashInfer"
+    )
+    parser.add_argument(
+        "--models",
+        nargs="+",
+        type=str,
+        default=["meta-llama/Llama-3.1-8B-Instruct"],
+        choices=list(WEIGHT_SHAPES.keys()),
+    )
+    parser.add_argument("--tp-sizes", nargs="+", type=int, default=[1])
+    parser.add_argument(
+        "--save-path",
+        type=str,
+        default=None,
+        help="Path to save benchmark results",
+    )
+    parser.add_argument(
+        "--accuracy",
+        action="store_true",
+        help="Run accuracy tests",
+    )
+    args = parser.parse_args()
+
+    if args.accuracy:
+        test_accuracy()
+
+    for K, N, model in prepare_shapes(args):
+        print(f"\n{model}, N={N} K={K}")
+        benchmark.run(
+            print_data=True,
+            save_path=args.save_path,
+            N=N,
+            K=K,
+        )
+
+    print("\nBenchmark finished!")

benchmarks/kernels/benchmark_activation.py

@@ -8,13 +8,12 @@ import torch
 
 import vllm.model_executor.layers.activation  # noqa F401
 from vllm.model_executor.custom_op import CustomOp
-from vllm.platforms import current_platform
 from vllm.triton_utils import triton
 from vllm.utils.argparse_utils import FlexibleArgumentParser
-from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE
+from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE, set_random_seed
 
-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))
 
@@ -30,7 +29,7 @@ def benchmark_activation(
     device = "cuda"
     num_tokens = batch_size * seq_len
     dim = intermediate_size
-    current_platform.seed_everything(42)
+    set_random_seed(42)
     torch.set_default_device(device)
 
     if func_name == "gelu_and_mul":

benchmarks/kernels/benchmark_cutlass_moe_fp8.py

@@ -6,15 +6,19 @@ kernel. Both kernels take in fp8 quantized weights and 16-bit activations,
 but use different quantization strategies and backends.
 """
 
-import nvtx
 import torch
 
+import vllm.model_executor.layers.fused_moe.modular_kernel as mk
 from vllm import _custom_ops as ops
 from vllm.model_executor.layers.fused_moe.config import fp8_w8a8_moe_quant_config
-from vllm.model_executor.layers.fused_moe.cutlass_moe import cutlass_moe_fp8
+from vllm.model_executor.layers.fused_moe.cutlass_moe import CutlassExpertsFp8
 from vllm.model_executor.layers.fused_moe.fused_moe import fused_experts, fused_topk
+from vllm.model_executor.layers.fused_moe.prepare_finalize import (
+    MoEPrepareAndFinalizeNoEP,
+)
 from vllm.platforms import current_platform
 from vllm.utils.argparse_utils import FlexibleArgumentParser
+from vllm.v1.worker.workspace import init_workspace_manager
 
 # Weight shapes for different models: [num_experts, topk, hidden_size,
 # intermediate_size]
@@ -58,6 +62,7 @@ def bench_run(
     per_out_ch: bool,
     mkn: tuple[int, int, int],
 ):
+    init_workspace_manager(torch.cuda.current_device())
     (m, k, n) = mkn
 
     dtype = torch.half
@@ -120,85 +125,6 @@ def bench_run(
     # Force per-tensor quantization for all cases
     per_act_token = False
 
-    # Create stride tensors for CUTLASS
-    ab_strides1 = torch.full((num_experts,), k, dtype=torch.int64, device=device)
-    ab_strides2 = torch.full((num_experts,), n, dtype=torch.int64, device=device)
-    c_strides1 = torch.full((num_experts,), 2 * n, dtype=torch.int64, device=device)
-    c_strides2 = torch.full((num_experts,), k, dtype=torch.int64, device=device)
-
-    def run_triton_moe(
-        a: torch.Tensor,
-        w1: torch.Tensor,
-        w2: torch.Tensor,
-        topk_weights: torch.Tensor,
-        topk_ids: torch.Tensor,
-        w1_scale: torch.Tensor,
-        w2_scale: torch.Tensor,
-        a1_scale: torch.Tensor,
-        a2_scale: torch.Tensor,
-        num_repeats: int,
-    ):
-        quant_config = fp8_w8a8_moe_quant_config(
-            w1_scale=w1_scale,
-            w2_scale=w2_scale,
-            a1_scale=a1_scale,
-            a2_scale=a2_scale,
-            per_act_token_quant=per_act_token,
-            per_out_ch_quant=per_out_ch,
-        )
-
-        for _ in range(num_repeats):
-            fused_experts(
-                a,
-                w1,
-                w2,
-                topk_weights,
-                topk_ids,
-                quant_config=quant_config,
-            )
-
-    def run_cutlass_moe_fp8(
-        a: torch.Tensor,
-        w1: torch.Tensor,
-        w2: torch.Tensor,
-        topk_weights: torch.Tensor,
-        topk_ids: torch.Tensor,
-        ab_strides1: torch.Tensor,
-        ab_strides2: torch.Tensor,
-        c_strides1: torch.Tensor,
-        c_strides2: torch.Tensor,
-        w1_scale: torch.Tensor,
-        w2_scale: torch.Tensor,
-        a1_scale: torch.Tensor,
-        a2_scale: torch.Tensor,
-        num_repeats: int,
-    ):
-        quant_config = fp8_w8a8_moe_quant_config(
-            w1_scale=w1_scale,
-            w2_scale=w2_scale,
-            a1_scale=a1_scale,
-            a2_scale=a2_scale,
-            per_act_token_quant=per_act_token,
-            per_out_ch_quant=per_out_ch,
-        )
-
-        for _ in range(num_repeats):
-            with nvtx.annotate("cutlass_moe_fp8", color="blue"):
-                cutlass_moe_fp8(
-                    a=a,
-                    w1_q=w1,
-                    w2_q=w2,
-                    topk_weights=topk_weights,
-                    topk_ids=topk_ids,
-                    ab_strides1=ab_strides1,
-                    ab_strides2=ab_strides2,
-                    c_strides1=c_strides1,
-                    c_strides2=c_strides2,
-                    quant_config=quant_config,
-                    activation="silu",
-                    global_num_experts=num_experts,
-                )
-
     # Pre-create quantization config to avoid creating it inside CUDA graph
     quant_config = fp8_w8a8_moe_quant_config(
         w1_scale=w1_scale,
@@ -209,23 +135,30 @@ def bench_run(
         per_out_ch_quant=per_out_ch,
     )
 
+    fn = mk.FusedMoEModularKernel(
+        MoEPrepareAndFinalizeNoEP(),
+        CutlassExpertsFp8(
+            out_dtype=a.dtype,
+            e=num_experts,
+            n=n,
+            k=k,
+            quant_config=quant_config,
+            device=w1.device,
+        ),
+    )
+
     # Create CUDA graphs for CUTLASS (match benchmark_moe.py pattern exactly)
     cutlass_stream = torch.cuda.Stream()
     cutlass_graph = torch.cuda.CUDAGraph()
     with torch.cuda.graph(cutlass_graph, stream=cutlass_stream):
         # Capture 10 invocations like benchmark_moe.py
         for _ in range(10):
-            cutlass_moe_fp8(
-                a=a,
-                w1_q=w1_fp8q_cutlass,
-                w2_q=w2_fp8q_cutlass,
-                topk_weights=topk_weights,
-                topk_ids=topk_ids,
-                ab_strides1=ab_strides1,
-                ab_strides2=ab_strides2,
-                c_strides1=c_strides1,
-                c_strides2=c_strides2,
-                quant_config=quant_config,
+            fn(
+                a,
+                w1_fp8q_cutlass,
+                w2_fp8q_cutlass,
+                topk_weights,
+                topk_ids,
                 activation="silu",
                 global_num_experts=num_experts,
             )
@@ -297,6 +230,10 @@ def bench_run(
 
 
 def main(args):
+    # Initialize workspace manager (required for CUTLASS MoE kernels)
+    device = torch.device("cuda:0")
+    init_workspace_manager(device)
+
     print("Benchmarking models:")
     for i, model in enumerate(args.models):
         print(f"[{i}]  {model}")

benchmarks/kernels/benchmark_cutlass_fp4_moe.py → benchmarks/kernels/benchmark_cutlass_moe_nvfp4.py

@@ -11,16 +11,23 @@ import nvtx
 import torch
 import torch.utils.benchmark as benchmark
 
+import vllm.model_executor.layers.fused_moe.modular_kernel as mk
 from vllm import _custom_ops as ops
 from vllm.config import ParallelConfig, VllmConfig, set_current_vllm_config
 from vllm.model_executor.layers.fused_moe.config import (
     fp8_w8a8_moe_quant_config,
     nvfp4_moe_quant_config,
 )
-from vllm.model_executor.layers.fused_moe.cutlass_moe import cutlass_moe_fp4
+from vllm.model_executor.layers.fused_moe.cutlass_moe import (
+    CutlassExpertsFp4,
+)
 from vllm.model_executor.layers.fused_moe.fused_moe import fused_experts, fused_topk
+from vllm.model_executor.layers.fused_moe.prepare_finalize import (
+    MoEPrepareAndFinalizeNoEP,
+)
 from vllm.scalar_type import scalar_types
 from vllm.utils.argparse_utils import FlexibleArgumentParser
+from vllm.v1.worker.workspace import init_workspace_manager
 
 WEIGHT_SHAPES_MOE = {
     "nvidia/DeepSeek-R1-FP4": [
@@ -187,19 +194,24 @@ def bench_run(
             g1_alphas=w1_gs,
             g2_alphas=w2_gs,
         )
+
+        kernel = mk.FusedMoEModularKernel(
+            MoEPrepareAndFinalizeNoEP(defer_input_quant=True),
+            CutlassExpertsFp4(
+                out_dtype=dtype,
+                max_experts_per_worker=e,
+                quant_config=quant_config,
+            ),
+        )
+
         for _ in range(num_repeats):
             with nvtx.annotate("cutlass_moe_fp4", color="green"):
-                cutlass_moe_fp4(
-                    a=a,
-                    w1_fp4=w1_fp4,
-                    w2_fp4=w2_fp4,
+                kernel(
+                    hidden_states=a,
+                    w1=w1_fp4,
+                    w2=w2_fp4,
                     topk_weights=topk_weights,
                     topk_ids=topk_ids,
-                    m=m,
-                    n=n,
-                    k=k,
-                    e=num_experts,
-                    quant_config=quant_config,
                 )
 
     def run_cutlass_from_graph(
@@ -229,20 +241,24 @@ def bench_run(
             g2_alphas=w2_gs,
         )
 
+        kernel = mk.FusedMoEModularKernel(
+            MoEPrepareAndFinalizeNoEP(defer_input_quant=True),
+            CutlassExpertsFp4(
+                out_dtype=dtype,
+                max_experts_per_worker=e,
+                quant_config=quant_config,
+            ),
+        )
+
         with set_current_vllm_config(
             VllmConfig(parallel_config=ParallelConfig(pipeline_parallel_size=1))
         ):
-            return cutlass_moe_fp4(
-                a=a,
-                w1_fp4=w1_fp4,
-                w2_fp4=w2_fp4,
+            return kernel(
+                hidden_states=a,
+                w1=w1_fp4,
+                w2=w2_fp4,
                 topk_weights=topk_weights,
                 topk_ids=topk_ids,
-                m=m,
-                n=n,
-                k=k,
-                e=num_experts,
-                quant_config=quant_config,
             )
 
     def run_triton_from_graph(
@@ -441,6 +457,10 @@ def bench_run(
 
 
 def main(args):
+    # Initialize workspace manager (required for CUTLASS MoE kernels)
+    device = torch.device("cuda:0")
+    init_workspace_manager(device)
+
     print("Benchmarking models:")
     for i, model in enumerate(args.models):
         print(f"[{i}]  {model}")

benchmarks/kernels/benchmark_device_communicators.py

@@ -293,7 +293,7 @@ class CommunicatorBenchmark:
                     graph = torch.cuda.CUDAGraph()
                     graph_pool = torch.cuda.graph_pool_handle()
                     set_graph_pool_id(graph_pool)
-                    with torch.cuda.graph(graph, pool=graph_pool):
+                    with torch.cuda.graph(graph, pool=graph_pool, stream=stream):
                         for _ in range(CUDA_GRAPH_CAPTURE_CYCLES):
                             allreduce_fn(graph_input)
 

benchmarks/kernels/benchmark_grouped_gemm_cutlass.py

@@ -5,15 +5,20 @@ import torch
 import torch.utils.benchmark as benchmark
 from benchmark_shapes import WEIGHT_SHAPES_MOE
 
+import vllm.model_executor.layers.fused_moe.modular_kernel as mk
 from vllm import _custom_ops as ops
 from vllm.config import ParallelConfig, VllmConfig, set_current_vllm_config
 from vllm.model_executor.layers.fused_moe.config import fp8_w8a8_moe_quant_config
-from vllm.model_executor.layers.fused_moe.cutlass_moe import cutlass_moe_fp8
+from vllm.model_executor.layers.fused_moe.cutlass_moe import CutlassExpertsFp8
 from vllm.model_executor.layers.fused_moe.fused_moe import (
     fused_experts,
     fused_topk,
 )
+from vllm.model_executor.layers.fused_moe.prepare_finalize import (
+    MoEPrepareAndFinalizeNoEP,
+)
 from vllm.utils.argparse_utils import FlexibleArgumentParser
+from vllm.v1.worker.workspace import init_workspace_manager
 
 DEFAULT_MODELS = [
     "mistralai/Mixtral-8x7B-Instruct-v0.1",
@@ -44,6 +49,7 @@ def bench_run(
     per_out_ch: bool,
     mkn: tuple[int, int, int],
 ):
+    init_workspace_manager(torch.cuda.current_device())
     label = "Quant Matmul"
 
     sub_label = (
@@ -81,11 +87,6 @@ def bench_run(
         a, score, topk, renormalize=False
     )
 
-    ab_strides1 = torch.full((num_experts,), k, device="cuda", dtype=torch.int64)
-    ab_strides2 = torch.full((num_experts,), n, device="cuda", dtype=torch.int64)
-    c_strides1 = torch.full((num_experts,), 2 * n, device="cuda", dtype=torch.int64)
-    c_strides2 = torch.full((num_experts,), k, device="cuda", dtype=torch.int64)
-
     def run_triton_moe(
         a: torch.Tensor,
         w1: torch.Tensor,
@@ -119,10 +120,6 @@ def bench_run(
         w2: torch.Tensor,
         w1_scale: torch.Tensor,
         w2_scale: torch.Tensor,
-        ab_strides1: torch.Tensor,
-        ab_strides2: torch.Tensor,
-        c_strides1: torch.Tensor,
-        c_strides2: torch.Tensor,
         topk_weights: torch.Tensor,
         topk_ids: torch.Tensor,
         per_act_token: bool,
@@ -134,31 +131,29 @@ def bench_run(
             per_act_token_quant=per_act_token,
         )
 
-        for _ in range(num_repeats):
-            cutlass_moe_fp8(
-                a,
-                w1,
-                w2,
-                topk_weights,
-                topk_ids,
-                ab_strides1,
-                ab_strides2,
-                c_strides1,
-                c_strides2,
+        fn = mk.FusedMoEModularKernel(
+            MoEPrepareAndFinalizeNoEP(),
+            CutlassExpertsFp8(
+                out_dtype=a.dtype,
+                # NOTE(rob): w2 is shaped as [E, hidden, intermediate]
+                e=w2.shape[0],
+                n=w2.shape[2],
+                k=w2.shape[1],
                 quant_config=quant_config,
-            )
+                device=w1.device,
+            ),
+        )
+
+        for _ in range(num_repeats):
+            fn(a, w1, w2, topk_weights, topk_ids)
 
     def run_cutlass_from_graph(
         a: torch.Tensor,
         a_scale: torch.Tensor,
-        w1_q: torch.Tensor,
-        w2_q: torch.Tensor,
+        w1: torch.Tensor,
+        w2: torch.Tensor,
         w1_scale: torch.Tensor,
         w2_scale: torch.Tensor,
-        ab_strides1: torch.Tensor,
-        ab_strides2: torch.Tensor,
-        c_strides1: torch.Tensor,
-        c_strides2: torch.Tensor,
         topk_weights: torch.Tensor,
         topk_ids: torch.Tensor,
     ):
@@ -168,21 +163,23 @@ def bench_run(
             per_act_token_quant=per_act_token,
         )
 
+        fn = mk.FusedMoEModularKernel(
+            MoEPrepareAndFinalizeNoEP(),
+            CutlassExpertsFp8(
+                out_dtype=a.dtype,
+                # NOTE(rob): w2 is shaped as [E, hidden, intermediate]
+                e=w2.shape[0],
+                n=w2.shape[2],
+                k=w2.shape[1],
+                quant_config=quant_config,
+                device=w1.device,
+            ),
+        )
+
         with set_current_vllm_config(
             VllmConfig(parallel_config=ParallelConfig(pipeline_parallel_size=1))
         ):
-            return cutlass_moe_fp8(
-                a,
-                w1_q,
-                w2_q,
-                topk_weights,
-                topk_ids,
-                ab_strides1,
-                ab_strides2,
-                c_strides1,
-                c_strides2,
-                quant_config=quant_config,
-            )
+            return fn(a, w1, w2, topk_weights, topk_ids)
 
     def run_triton_from_graph(
         a: torch.Tensor,
@@ -226,10 +223,6 @@ def bench_run(
             w2_q,
             w1_scale,
             w2_scale,
-            ab_strides1,
-            ab_strides2,
-            c_strides1,
-            c_strides2,
             topk_weights,
             topk_ids,
         )
@@ -267,10 +260,6 @@ def bench_run(
         "w1_scale": w1_scale,
         "w2_scale": w2_scale,
         "per_act_token": per_act_token,
-        "ab_strides1": ab_strides1,
-        "ab_strides2": ab_strides2,
-        "c_strides1": c_strides1,
-        "c_strides2": c_strides2,
         # cuda graph params
         "cutlass_graph": cutlass_graph,
         "triton_graph": triton_graph,
@@ -329,10 +318,6 @@ def bench_run(
         w2_q,
         w1_scale,
         w2_scale,
-        ab_strides1,
-        ab_strides2,
-        c_strides1,
-        c_strides2,
         topk_weights,
         topk_ids,
         per_act_token,
@@ -341,7 +326,7 @@ def bench_run(
 
     results.append(
         benchmark.Timer(
-            stmt="run_cutlass_moe(a, a_scale, w1_q, w2_q, w1_scale, w2_scale, ab_strides1, ab_strides2, c_strides1, c_strides2, topk_weights, topk_ids, per_act_token, num_runs)",  # noqa: E501
+            stmt="run_cutlass_moe(a, a_scale, w1_q, w2_q, w1_scale, w2_scale, topk_weights, topk_ids, per_act_token, num_runs)",  # noqa: E501
             globals=globals,
             label=label,
             sub_label=sub_label,
@@ -364,6 +349,10 @@ def bench_run(
 
 
 def main(args):
+    # Initialize workspace manager (required for CUTLASS MoE kernels)
+    device = torch.device("cuda:0")
+    init_workspace_manager(device)
+
     print("Benchmarking models:")
     for i, model in enumerate(args.models):
         print(f"[{i}]  {model}")

benchmarks/kernels/benchmark_layernorm.py

@@ -6,9 +6,8 @@ import time
 import torch
 
 from vllm.model_executor.layers.layernorm import RMSNorm
-from vllm.platforms import current_platform
 from vllm.utils.argparse_utils import FlexibleArgumentParser
-from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE
+from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE, set_random_seed
 
 
 @torch.inference_mode()
@@ -22,7 +21,7 @@ def main(
     num_warmup_iters: int = 5,
     num_iters: int = 100,
 ) -> None:
-    current_platform.seed_everything(seed)
+    set_random_seed(seed)
     torch.set_default_device("cuda")
 
     layer = RMSNorm(hidden_size).to(dtype=dtype)

benchmarks/kernels/benchmark_moe.py

@@ -2,6 +2,7 @@
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import argparse
+import gc
 import json
 import os
 import time
@@ -22,10 +23,49 @@ from vllm.model_executor.layers.fused_moe.fused_moe import *
 from vllm.transformers_utils.config import get_config
 from vllm.triton_utils import triton
 from vllm.utils.argparse_utils import FlexibleArgumentParser
+from vllm.utils.torch_utils import set_random_seed
 
 # 移除全局的 current_platform 导入，改为在需要时局部导入
 # FP8_DTYPE = current_platform.fp8_dtype()
 
+# Default interval for clearing Triton JIT cache during tuning
+# Set to 0 to disable automatic cache clearing
+_CACHE_CLEAR_INTERVAL_ENV = "VLLM_MOE_TUNE_CACHE_CLEAR_INTERVAL"
+TRITON_CACHE_CLEAR_INTERVAL = int(os.environ.get(_CACHE_CLEAR_INTERVAL_ENV, "50"))
+
+
+def clear_triton_cache():
+    """Clear Triton JIT compilation cache and Python/CUDA memory.
+
+    This helps prevent OOM during tuning with large models (many experts).
+    """
+    # Force Python garbage collection
+    gc.collect()
+
+    # Clear CUDA memory cache
+    if torch.cuda.is_available():
+        torch.cuda.empty_cache()
+
+    # Try to clear Triton's runtime cache
+    try:
+        if (
+            hasattr(triton, "runtime")
+            and hasattr(triton.runtime, "cache")
+            and hasattr(triton.runtime.cache, "clear")
+        ):
+            triton.runtime.cache.clear()
+    except ImportError:
+        # Triton not installed, skip cache clearing
+        pass
+    except AttributeError:
+        # Triton version doesn't have expected cache API
+        pass
+    except Exception as e:
+        print(f"Warning: Failed to clear Triton cache: {e}")
+
+    # Additional garbage collection after clearing caches
+    gc.collect()
+
 
 def ensure_divisibility(numerator, denominator, text):
     """Ensure that numerator is divisible by the denominator."""
@@ -454,7 +494,8 @@ class BenchmarkWorker:
             pass
         else:
             torch.set_default_device("cuda:"+ str(device_id))
-        current_platform.seed_everything(seed)
+
+        set_random_seed(seed)
         self.seed = seed
         # Store the logical device ID for Ray
         self.device_id = device_id
@@ -475,7 +516,10 @@ class BenchmarkWorker:
     ) -> tuple[dict[str, int], float]:
         # 局部导入 current_platform
         from vllm.platforms import current_platform
-        current_platform.seed_everything(self.seed)
+        
+        from vllm.model_executor.layers.fused_moe.fused_moe import  get_moe_configs, get_default_config
+
+        set_random_seed(self.seed)
         dtype_str = _get_config_dtype_str(
             dtype, use_int8_w8a16=use_int8_w8a16, use_fp8_w8a8=use_fp8_w8a8
         )
@@ -560,7 +604,7 @@ class BenchmarkWorker:
                 need_device_guard = True
 
         with torch.cuda.device(self.device_id) if need_device_guard else nullcontext():
-            for config in tqdm(search_space):
+            for idx, config in enumerate(tqdm(search_space)):
                 try:
                     kernel_time = benchmark_config(
                         config,
@@ -583,6 +627,19 @@ class BenchmarkWorker:
                 if kernel_time < best_time:
                     best_time = kernel_time
                     best_config = config
+
+                # Periodically clear Triton JIT cache to prevent OOM
+                # This is especially important for large models with many experts
+                if (
+                    TRITON_CACHE_CLEAR_INTERVAL > 0
+                    and idx > 0
+                    and idx % TRITON_CACHE_CLEAR_INTERVAL == 0
+                ):
+                    clear_triton_cache()
+
+        # Final cleanup after tuning completes
+        clear_triton_cache()
+
         now = datetime.now()
         print(f"{now.ctime()}] Completed tuning for batch_size={num_tokens}")
         assert best_config is not None

benchmarks/kernels/benchmark_moe_permute_unpermute.py

@@ -18,6 +18,7 @@ from vllm.model_executor.layers.fused_moe.moe_permute_unpermute import (
 from vllm.model_executor.layers.fused_moe.utils import _fp8_quantize
 from vllm.platforms import current_platform
 from vllm.utils.argparse_utils import FlexibleArgumentParser
+from vllm.utils.torch_utils import set_random_seed
 
 FP8_DTYPE = current_platform.fp8_dtype()
 
@@ -261,7 +262,7 @@ def benchmark_unpermute(
 class BenchmarkWorker:
     def __init__(self, seed: int) -> None:
         torch.set_default_device("cuda")
-        current_platform.seed_everything(seed)
+        set_random_seed(seed)
         self.seed = seed
         # Get the device ID to allocate tensors and kernels
         # on the respective GPU. This is required for Ray to work
@@ -279,7 +280,7 @@ class BenchmarkWorker:
         use_int8_w8a16: bool,
         use_customized_permute: bool = False,
     ) -> tuple[dict[str, int], float]:
-        current_platform.seed_everything(self.seed)
+        set_random_seed(self.seed)
 
         permute_time = benchmark_permute(
             num_tokens,

benchmarks/kernels/benchmark_mrope.py

@@ -37,9 +37,9 @@ import numpy as np
 import torch
 
 from vllm.model_executor.layers.rotary_embedding import get_rope
-from vllm.platforms import current_platform
 from vllm.transformers_utils.config import get_config
 from vllm.utils.argparse_utils import FlexibleArgumentParser
+from vllm.utils.torch_utils import set_random_seed
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
@@ -94,7 +94,7 @@ def benchmark_mrope(
     benchmark_iter: int = 100,
     csv_writer=None,
 ):
-    current_platform.seed_everything(seed)
+    set_random_seed(seed)
     torch.set_default_device(device)
     # the parameters to compute the q k v size based on tp_size
     mrope_helper_class = get_rope(

benchmarks/kernels/benchmark_paged_attention.py

@@ -13,6 +13,7 @@ from vllm.utils.argparse_utils import FlexibleArgumentParser
 from vllm.utils.torch_utils import (
     STR_DTYPE_TO_TORCH_DTYPE,
     create_kv_caches_with_random,
+    set_random_seed,
 )
 import vllm.envs as envs
 
@@ -39,7 +40,7 @@ def main(
     device: str = "cuda",
     kv_cache_dtype: str | None = None,
 ) -> None:
-    current_platform.seed_everything(seed)
+    set_random_seed(seed)
 
     scale = float(1.0 / (head_size**0.5))
     query = torch.empty(

benchmarks/kernels/benchmark_quant.py

@@ -6,9 +6,8 @@ import time
 import torch
 
 from vllm import _custom_ops as ops
-from vllm.platforms import current_platform
 from vllm.utils.argparse_utils import FlexibleArgumentParser
-from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE
+from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE, set_random_seed
 
 
 @torch.inference_mode()
@@ -23,7 +22,7 @@ def main(
     num_warmup_iters: int = 5,
     num_iters: int = 100,
 ) -> None:
-    current_platform.seed_everything(seed)
+    set_random_seed(seed)
     torch.set_default_device("cuda")
 
     x = torch.randn(num_tokens, hidden_size, dtype=dtype)