diff --git a/container/Dockerfile.vllm b/container/Dockerfile.vllm index 776ff9bf6be..cccb48c3564 100644 --- a/container/Dockerfile.vllm +++ b/container/Dockerfile.vllm @@ -75,7 +75,7 @@ ARG RUNTIME_IMAGE_TAG="12.9.1-runtime-ubuntu24.04" ARG CUDA_VERSION="12.9" # Make sure to update the dependency version in pyproject.toml when updating this -ARG VLLM_REF="v0.14.0" +ARG VLLM_REF="v0.14.1" # FlashInfer Ref used to install flashinfer-cubin and flashinfer-jit-cache ARG FLASHINF_REF="v0.5.3" diff --git a/container/deps/vllm/install_vllm.sh b/container/deps/vllm/install_vllm.sh index 88a5c494745..573a55af876 100755 --- a/container/deps/vllm/install_vllm.sh +++ b/container/deps/vllm/install_vllm.sh @@ -11,7 +11,7 @@ set -euo pipefail -VLLM_VER="0.14.0" +VLLM_VER="0.14.1" VLLM_REF="v${VLLM_VER}" # Basic Configurations diff --git a/docs/reference/support-matrix.md b/docs/reference/support-matrix.md index be288caf862..3650f1db12f 100644 --- a/docs/reference/support-matrix.md +++ b/docs/reference/support-matrix.md @@ -16,7 +16,7 @@ The following table shows the backend framework versions included with each Dyna | **Dependency** | **main (ToT)** | **v0.8.1.post1** | **v0.8.1 (latest)** | **v0.8.0** | **v0.7.1** | **v0.7.0.post1** | **v0.7.0** | | :------------- | :------------- | :--------------- | :------------------ | :--------- | :--------- | :--------------- | :--------- | -| vLLM | `0.14.0` | `0.12.0` | `0.12.0` | `0.12.0` | `0.11.0` | `0.11.0` | `0.11.0` | +| vLLM | `0.14.1` | `0.12.0` | `0.12.0` | `0.12.0` | `0.11.0` | `0.11.0` | `0.11.0` | | SGLang | `0.5.8` | `0.5.6.post2` | `0.5.6.post2` | `0.5.6.post2` | `0.5.3.post4` | `0.5.3.post4` | `0.5.3.post4` | | TensorRT-LLM | `1.2.0rc6.post2` | `1.2.0rc6.post2` | `1.2.0rc6.post1` | `1.2.0rc6.post1` | `1.2.0rc3` | `1.2.0rc3` | `1.2.0rc2` | | NIXL | `0.9.0` | `0.8.0` | `0.8.0` | `0.8.0` | `0.8.0` | `0.8.0` | `0.8.0` | diff --git a/pyproject.toml b/pyproject.toml index b0e062c00fd..6df4069affc 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -56,7 +56,7 @@ trtllm =[ vllm = [ "uvloop", "nixl[cu12]<=0.9.0", - "vllm[flashinfer,runai]==0.14.0", + "vllm[flashinfer,runai]==0.14.1", ] sglang = [