Merge branch 'master' into fix-neuron

ahsan-z-khan · web-flow · commit 544010ca3aaf · 2025-09-18T10:31:07.000-07:00
diff --git a/vllm/buildspec.yml b/vllm/buildspec.yml
@@ -2,7 +2,7 @@ account_id: &ACCOUNT_ID <set-$ACCOUNT_ID-in-environment>
 prod_account_id: &PROD_ACCOUNT_ID 763104351884
 region: &REGION <set-$REGION-in-environment>
 framework: &FRAMEWORK vllm
-version: &VERSION "0.10.1"
+version: &VERSION "0.10.2"
 short_version: &SHORT_VERSION "0.10"
 arch_type: &ARCH_TYPE x86_64
 autopatch_build: "False"
@@ -35,7 +35,7 @@ images:
       <<: *BUILD_CONTEXT
     image_size_baseline: 20000
     device_type: &DEVICE_TYPE gpu
-    cuda_version: &CUDA_VERSION cu128
+    cuda_version: &CUDA_VERSION cu129
     python_version: &DOCKER_PYTHON_VERSION py3
     tag_python_version: &TAG_PYTHON_VERSION py312
     os_version: &OS_VERSION ubuntu22.04
diff --git a/vllm/x86_64/gpu/Dockerfile b/vllm/x86_64/gpu/Dockerfile
@@ -1,4 +1,4 @@
-FROM docker.io/vllm/vllm-openai:v0.10.1.1 as final
+FROM docker.io/vllm/vllm-openai:v0.10.2 as final
 ARG PYTHON="python3"
 ARG EFA_VERSION="1.43.2"
 LABEL maintainer="Amazon AI"

Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-FROM docker.io/vllm/vllm-openai:v0.10.1.1 as final`
	`1`	`+FROM docker.io/vllm/vllm-openai:v0.10.2 as final`
`2`	`2`	`ARG PYTHON="python3"`
`3`	`3`	`ARG EFA_VERSION="1.43.2"`
`4`	`4`	`LABEL maintainer="Amazon AI"`