python3Packages.vllm: 0.10.2 -> 0.11.0 (#448598)

diff --git a/requirements/cpu.txt b/requirements/cpu.txt

index d80354342..7434f32f0 100644

index 2db6d87ee..37f816170 100644

--- a/requirements/cpu.txt

+++ b/requirements/cpu.txt

@@ -21,7 +21,4 @@ torchvision; platform_machine != "ppc64le" and platform_machine != "s390x"

 torchvision==0.22.0; platform_machine == "ppc64le"

@@ -21,9 +21,6 @@ torchvision; platform_machine != "ppc64le" and platform_machine != "s390x"

 torchvision==0.23.0; platform_machine == "ppc64le"

 datasets # for benchmark scripts

-# Intel Extension for PyTorch, only for x86_64 CPUs

-intel-openmp==2024.2.1; platform_machine == "x86_64"

-intel_extension_for_pytorch==2.6.0; platform_machine == "x86_64" # torch>2.6.0+cpu has performance regression on x86 platform, see https://github.com/pytorch/pytorch/pull/151218

-intel_extension_for_pytorch==2.8.0; platform_machine == "x86_64"

 triton==3.2.0; platform_machine == "x86_64" # Triton is required for torch 2.6+cpu, as it is imported in torch.compile.

 # Use this to gather CPU info and optimize based on ARM Neoverse cores

    src = fetchFromGitHub {

      owner = "vllm-project";

      repo = "FlashMLA";

      rev = "a757314c04eedd166e329e846c820eb1bdd702de";

      hash = "sha256-KT9R6ju7XzgqKHPGQwzw0yNiKL3DNW6qJrEBvmLn4hY=";

      rev = "5f65b85703c7ed75fda01e06495077caad207c3f";

      hash = "sha256-DO9EFNSoAgyfRRc095v1UjT+Zdzk4cFY0+n28FVEwI0=";

    };

    dontConfigure = true;

buildPythonPackage rec {

  pname = "vllm";

  version = "0.10.2";

  version = "0.11.0";

  pyproject = true;

  stdenv = torch.stdenv;

    owner = "vllm-project";

    repo = "vllm";

    tag = "v${version}";

    hash = "sha256-m9P4cxxdAToGKKIyTQdFupG3vZ3sEueMMxjugYfjKbo=";

    hash = "sha256-uYK/e9McEyrDTACMk5S0cGCjai9rf6HMR9dpPL7ISYc=";

  };

  patches = [