chore(deps): bump vLLM to 0.15.1 (#6102)

Signed-off-by: alec-flowers <aflowers@nvidia.com>
Signed-off-by: Alec <35311602+alec-flowers@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>

container/context.yaml

@@ -38,9 +38,9 @@ vllm:
     base_image_tag: 25.06-cuda12.9-devel-ubuntu24.04
   cuda13.0:
     base_image_tag: 25.11-cuda13.0-devel-ubuntu24.04
-  vllm_ref: v0.14.1
-  flashinf_ref: v0.5.3
-  lmcache_ref: 0.3.12
+  vllm_ref: v0.15.1
+  flashinf_ref: v0.6.1
+  lmcache_ref: 0.3.13
   max_jobs: "10"
   enable_media_ffmpeg: "true"
   enable_gpu_memory_service: "true"

container/deps/vllm/install_vllm.sh

@@ -11,7 +11,7 @@
 
 set -euo pipefail
 
-VLLM_VER="0.14.1"
+VLLM_VER="0.15.1"
 VLLM_REF="v${VLLM_VER}"
 
 # Basic Configurations
@@ -23,8 +23,8 @@ INSTALLATION_DIR=/tmp
 TORCH_CUDA_ARCH_LIST="9.0;10.0" # For EP Kernels -- TODO: check if we need to add 12.0+PTX
 DEEPGEMM_REF=""
 CUDA_VERSION="12.9"
-FLASHINF_REF="v0.5.3"
-LMCACHE_REF="0.3.12"
+FLASHINF_REF="v0.6.1"
+LMCACHE_REF="0.3.13"
 
 while [[ $# -gt 0 ]]; do
     case $1 in

docs/reference/support-matrix.md

@@ -16,7 +16,7 @@ The following table shows the backend framework versions included with each Dyna
 
 | **Dynamo** | **vLLM** | **SGLang** | **TensorRT-LLM** | **NIXL** |
 | :--- | :--- | :--- | :--- | :--- |
-| **main (ToT)** | `0.14.1` | `0.5.8` | `1.3.0rc1` | `0.9.0` |
+| **main (ToT)** | `0.15.1` | `0.5.8` | `1.3.0rc1` | `0.9.0` |
 | **v1.0.0** *(planned)* | `0.15.0` | *Latest as of 2/17* | *Latest as of 2/17* | `0.10.0` |
 | **v0.9.0** *(in progress)* | `0.14.1` | `0.5.8` | `1.3.0rc1` | `0.9.0` |
 | **v0.8.1.post3** *(in progress)* | `0.12.0` | `0.5.6.post2` | `1.2.0rc6.post3` | `0.8.0` |

pyproject.toml

@@ -57,7 +57,7 @@ trtllm =[
 vllm = [
     "uvloop",
     "nixl[cu12]<=0.9.0",
-    "vllm[flashinfer,runai]==0.14.1",
+    "vllm[flashinfer,runai]==0.15.1",
     "vllm-omni==0.14.0",
 ]