From 740f781776805e7e126515e9920392522f00476d Mon Sep 17 00:00:00 2001
From: thxCode <3394724+thxCode@users.noreply.github.com>
Date: Fri, 18 Sep 2026 08:02:24 +0000
Subject: [PATCH] chore: update runner by gha workflow 35321925561

---
 gpustack_runner/runner.py.json                | 90 +++++++++++++++++++
 .../test_list_runners_by_backend.json         | 90 +++++++++++++++++++
 2 files changed, 180 insertions(+)

diff --git a/gpustack_runner/runner.py.json b/gpustack_runner/runner.py.json
index 6003ce7e..31a93bc9 100644
--- a/gpustack_runner/runner.py.json
+++ b/gpustack_runner/runner.py.json
@@ -1506,6 +1506,50 @@
     "docker_image": "gpustack/runner:cuda13.0-sglang0.5.12.post1",
     "deprecated": false
   },
+  {
+    "backend": "cuda",
+    "backend_version": "13.0",
+    "original_backend_version": "13.0.1",
+    "backend_variant": "",
+    "service": "vllm",
+    "service_version": "0.29.0",
+    "platform": "linux/amd64",
+    "docker_image": "gpustack/runner:cuda13.0-vllm0.29.0",
+    "deprecated": false,
+    "dependencies": {
+      "diffusers": "0.40.0",
+      "flashinfer-python": "0.6.18",
+      "lmcache": "0.5.4",
+      "ray": "2.54.0",
+      "runai-model-streamer": "0.16.1",
+      "torch": "2.13.0+cu130",
+      "transformers": "5.14.1",
+      "vllm-omni": "0.29.0rc1",
+      "vllm-router": "0.1.15"
+    }
+  },
+  {
+    "backend": "cuda",
+    "backend_version": "13.0",
+    "original_backend_version": "13.0.1",
+    "backend_variant": "",
+    "service": "vllm",
+    "service_version": "0.29.0",
+    "platform": "linux/arm64",
+    "docker_image": "gpustack/runner:cuda13.0-vllm0.29.0",
+    "deprecated": false,
+    "dependencies": {
+      "diffusers": "0.40.0",
+      "flashinfer-python": "0.6.18",
+      "lmcache": "0.5.4",
+      "ray": "2.54.0",
+      "runai-model-streamer": "0.16.1",
+      "torch": "2.13.0+cu130",
+      "transformers": "5.14.1",
+      "vllm-omni": "0.29.0rc2.dev0+gaff7d6494.d20260914",
+      "vllm-router": "0.1.15"
+    }
+  },
   {
     "backend": "cuda",
     "backend_version": "13.0",
@@ -1858,6 +1902,52 @@
     "docker_image": "gpustack/runner:cuda12.9-sglang0.5.6.post2",
     "deprecated": false
   },
+  {
+    "backend": "cuda",
+    "backend_version": "12.9",
+    "original_backend_version": "12.9.1",
+    "backend_variant": "",
+    "service": "vllm",
+    "service_version": "0.29.0",
+    "platform": "linux/amd64",
+    "docker_image": "gpustack/runner:cuda12.9-vllm0.29.0",
+    "deprecated": false,
+    "dependencies": {
+      "diffusers": "0.40.0",
+      "flashinfer-python": "0.6.18",
+      "lmcache": "0.5.4",
+      "mooncake-transfer-engine": "0.3.13.post1",
+      "ray": "2.54.0",
+      "runai-model-streamer": "0.16.1",
+      "torch": "2.13.0+cu129",
+      "transformers": "5.14.1",
+      "vllm-omni": "0.29.0rc1",
+      "vllm-router": "0.1.15"
+    }
+  },
+  {
+    "backend": "cuda",
+    "backend_version": "12.9",
+    "original_backend_version": "12.9.1",
+    "backend_variant": "",
+    "service": "vllm",
+    "service_version": "0.29.0",
+    "platform": "linux/arm64",
+    "docker_image": "gpustack/runner:cuda12.9-vllm0.29.0",
+    "deprecated": false,
+    "dependencies": {
+      "diffusers": "0.40.0",
+      "flashinfer-python": "0.6.18",
+      "lmcache": "0.5.4",
+      "mooncake-transfer-engine": "0.3.13.post1",
+      "ray": "2.54.0",
+      "runai-model-streamer": "0.16.1",
+      "torch": "2.13.0+cu129",
+      "transformers": "5.14.1",
+      "vllm-omni": "0.29.0rc2.dev0+gaff7d6494.d20260914",
+      "vllm-router": "0.1.15"
+    }
+  },
   {
     "backend": "cuda",
     "backend_version": "12.9",
diff --git a/tests/gpustack_runner/fixtures/test_list_runners_by_backend.json b/tests/gpustack_runner/fixtures/test_list_runners_by_backend.json
index 7a228379..7d61633c 100644
--- a/tests/gpustack_runner/fixtures/test_list_runners_by_backend.json
+++ b/tests/gpustack_runner/fixtures/test_list_runners_by_backend.json
@@ -1528,6 +1528,50 @@
         "docker_image": "gpustack/runner:cuda13.0-sglang0.5.12.post1",
         "deprecated": false
       },
+      {
+        "backend": "cuda",
+        "backend_version": "13.0",
+        "original_backend_version": "13.0.1",
+        "backend_variant": "",
+        "service": "vllm",
+        "service_version": "0.29.0",
+        "platform": "linux/amd64",
+        "docker_image": "gpustack/runner:cuda13.0-vllm0.29.0",
+        "deprecated": false,
+        "dependencies": {
+          "diffusers": "0.40.0",
+          "flashinfer-python": "0.6.18",
+          "lmcache": "0.5.4",
+          "ray": "2.54.0",
+          "runai-model-streamer": "0.16.1",
+          "torch": "2.13.0+cu130",
+          "transformers": "5.14.1",
+          "vllm-omni": "0.29.0rc1",
+          "vllm-router": "0.1.15"
+        }
+      },
+      {
+        "backend": "cuda",
+        "backend_version": "13.0",
+        "original_backend_version": "13.0.1",
+        "backend_variant": "",
+        "service": "vllm",
+        "service_version": "0.29.0",
+        "platform": "linux/arm64",
+        "docker_image": "gpustack/runner:cuda13.0-vllm0.29.0",
+        "deprecated": false,
+        "dependencies": {
+          "diffusers": "0.40.0",
+          "flashinfer-python": "0.6.18",
+          "lmcache": "0.5.4",
+          "ray": "2.54.0",
+          "runai-model-streamer": "0.16.1",
+          "torch": "2.13.0+cu130",
+          "transformers": "5.14.1",
+          "vllm-omni": "0.29.0rc2.dev0+gaff7d6494.d20260914",
+          "vllm-router": "0.1.15"
+        }
+      },
       {
         "backend": "cuda",
         "backend_version": "13.0",
@@ -1880,6 +1924,52 @@
         "docker_image": "gpustack/runner:cuda12.9-sglang0.5.6.post2",
         "deprecated": false
       },
+      {
+        "backend": "cuda",
+        "backend_version": "12.9",
+        "original_backend_version": "12.9.1",
+        "backend_variant": "",
+        "service": "vllm",
+        "service_version": "0.29.0",
+        "platform": "linux/amd64",
+        "docker_image": "gpustack/runner:cuda12.9-vllm0.29.0",
+        "deprecated": false,
+        "dependencies": {
+          "diffusers": "0.40.0",
+          "flashinfer-python": "0.6.18",
+          "lmcache": "0.5.4",
+          "mooncake-transfer-engine": "0.3.13.post1",
+          "ray": "2.54.0",
+          "runai-model-streamer": "0.16.1",
+          "torch": "2.13.0+cu129",
+          "transformers": "5.14.1",
+          "vllm-omni": "0.29.0rc1",
+          "vllm-router": "0.1.15"
+        }
+      },
+      {
+        "backend": "cuda",
+        "backend_version": "12.9",
+        "original_backend_version": "12.9.1",
+        "backend_variant": "",
+        "service": "vllm",
+        "service_version": "0.29.0",
+        "platform": "linux/arm64",
+        "docker_image": "gpustack/runner:cuda12.9-vllm0.29.0",
+        "deprecated": false,
+        "dependencies": {
+          "diffusers": "0.40.0",
+          "flashinfer-python": "0.6.18",
+          "lmcache": "0.5.4",
+          "mooncake-transfer-engine": "0.3.13.post1",
+          "ray": "2.54.0",
+          "runai-model-streamer": "0.16.1",
+          "torch": "2.13.0+cu129",
+          "transformers": "5.14.1",
+          "vllm-omni": "0.29.0rc2.dev0+gaff7d6494.d20260914",
+          "vllm-router": "0.1.15"
+        }
+      },
       {
         "backend": "cuda",
         "backend_version": "12.9",