support pd images for sglang:v0.5.11-cu130

Author: CementZhang

configs/inference/sglang.json

@@ -6,9 +6,9 @@
   "engine_images": [
     {
       "compute_type": "gpu",
-      "image": "opencsghq/sglang:v0.5.9-cu130",
+      "image": "opencsghq/sglang:v0.5.11-cu130",
       "driver_version": "13.0",
-      "engine_version": "v0.5.9",
+      "engine_version": "v0.5.11",
       "extra_archs": [
         "ApertusForCausalLM",
         "ArceeForCausalLM",
@@ -19,10 +19,11 @@
         "BailingMoeV2_5ForCausalLM",
         "BertForSequenceClassification",
         "BertModel",
-        "ChatGLMForConditionalGeneration",
         "Contriever",
-        "DeepseekOCR2ForCausalLM",
+        "ChatGLMForConditionalGeneration",
+        "DeepseekOCRForCausalLM",
         "DeepseekV32ForCausalLM",
+        "DotsOCRForCausalLM",
         "DotsVLMForCausalLM",
         "Ernie4_5_ForCausalLM",
         "Ernie4_5_MoeForCausalLM",
@@ -31,47 +32,72 @@
         "FalconH1ForCausalLM",
         "GPT2LMHeadModel",
         "GPTBigCodeForCausalLM",
+        "GPTJForCausalLM",
+        "Gemma4ForCausalLM",
+        "Gemma4ForConditionalGeneration",
         "Glm4ForCausalLM",
         "Glm4MoeForCausalLM",
         "Glm4MoeForCausalLMNextN",
+        "Glm4MoeLiteForCausalLM",
         "Glm4vForConditionalGeneration",
         "Glm4vMoeForConditionalGeneration",
+        "GlmAsrForConditionalGeneration",
         "GlmMoeDsaForCausalLM",
         "GlmOcrForConditionalGeneration",
+        "GlmOcrForConditionalGenerationNextN",
         "GptOssForCausalLM",
         "GraniteMoeHybridForCausalLM",
         "HunYuanDenseV1ForCausalLM",
         "HunYuanMoEV1ForCausalLM",
         "JetNemotronForCausalLM",
         "JetVLMForConditionalGeneration",
+        "KimiK25ForConditionalGeneration",
         "KimiLinearForCausalLM",
+        "KimiVLForConditionalGeneration",
         "LLaDA2MoeModelLM",
+        "LlavaForConditionalGeneration",
         "LlavaLlamaForCausalLM",
         "LlavaMistralForCausalLM",
         "LlavaQwenForCausalLM",
         "LongcatFlashForCausalLM",
         "LongcatFlashForCausalLMNextN",
+        "MiMoV2FlashForCausalLM",
+        "MiMoV2ForCausalLM",
+        "MiMoV2MTP",
         "MindSporeForCausalLM",
         "MiniMaxM2ForCausalLM",
         "Ministral3ForCausalLM",
+        "MistralForCausalLMEagle",
         "MistralLarge3ForCausalLM",
         "MistralLarge3ForCausalLMEagle",
-        "NemotronForCausalLM",
         "NemotronHForCausalLM",
+        "NemotronHForCausalLMMTP",
+        "NemotronH_Nano_Omni_Reasoning_V3",
         "NemotronH_Nano_VL_V2",
         "OPTForCausalLM",
         "OrionForCausalLM",
         "POINTSV15ChatModel",
         "PaddleOCRVLForConditionalGeneration",
         "Phi4FlashForCausalLM",
-        "Qwen3NextForCausalLM",
+        "Qwen2ForRewardModel",
+        "Qwen2ForSequenceClassification",
         "Qwen3_5MoeForConditionalGeneration",
+        "Qwen3ASRForConditionalGeneration",
+        "Qwen3ForRewardModel",
+        "Qwen3ForSequenceClassification",
+        "Qwen3NextForCausalLM",
+        "Qwen3NextForCausalLMMTP",
+        "Qwen3OmniMoeForConditionalGeneration",
+        "Qwen3VLForConditionalGeneration",
+        "Qwen3VLMoeForConditionalGeneration",
+        "Qwen3_5ForCausalLMMTP",
         "Qwen3_5ForConditionalGeneration",
         "Sarashina2VisionForCausalLM",
         "SmolLM3ForCausalLM",
         "SolarForCausalLM",
         "Starcoder2ForCausalLM",
         "Step3p5ForCausalLM",
+        "Step3p5MTP",
         "StepVLForConditionalGeneration",
         "TeleFLMForCausalLM",
         "VILAForConditionalGeneration"

docker/inference/Dockerfile.sglang

@@ -1,4 +1,4 @@
-FROM lmsysorg/sglang:v0.5.9-cu130
+FROM lmsysorg/sglang:v0.5.11-cu130
 RUN pip config set global.index-url https://mirrors.aliyun.com/pypi/simple
 RUN sed -i 's|http://archive.ubuntu.com/ubuntu|http://mirrors.aliyun.com/ubuntu|g' /etc/apt/sources.list && \
     sed -i 's|http://security.ubuntu.com/ubuntu|http://mirrors.aliyun.com/ubuntu|g' /etc/apt/sources.list && \