diff --git a/docs_new/cookbook/autoregressive/DeepSeek/DeepSeek-V3_2.mdx b/docs_new/cookbook/autoregressive/DeepSeek/DeepSeek-V3_2.mdx index 0ab97069f..e5c44234a 100644 --- a/docs_new/cookbook/autoregressive/DeepSeek/DeepSeek-V3_2.mdx +++ b/docs_new/cookbook/autoregressive/DeepSeek/DeepSeek-V3_2.mdx @@ -55,7 +55,7 @@ DeepSeek-V3.2 supports reasoning mode. Enable the reasoning parser during deploy ```shell Command sglang serve \ - --model deepseek-ai/DeepSeek-V3.2-Exp \ + --model-path deepseek-ai/DeepSeek-V3.2-Exp \ --reasoning-parser deepseek-v3 \ --tp 8 \ --host 0.0.0.0 \ @@ -139,7 +139,7 @@ For DeepSeek-V3.2-Exp: ```shell Command sglang serve \ - --model deepseek-ai/DeepSeek-V3.2-Exp \ + --model-path deepseek-ai/DeepSeek-V3.2-Exp \ --tool-call-parser deepseekv31 \ --reasoning-parser deepseek-v3 \ --chat-template ./examples/chat_template/tool_chat_template_deepseekv32.jinja \ diff --git a/docs_new/cookbook/autoregressive/GLM/GLM-5.mdx b/docs_new/cookbook/autoregressive/GLM/GLM-5.mdx index 9cb8af257..406e64aa1 100644 --- a/docs_new/cookbook/autoregressive/GLM/GLM-5.mdx +++ b/docs_new/cookbook/autoregressive/GLM/GLM-5.mdx @@ -101,7 +101,7 @@ Deploy GLM-5 with the following command (FP8 on H200, all features enabled): ```shell Command sglang serve \ - --model zai-org/GLM-5-FP8 \ + --model-path zai-org/GLM-5-FP8 \ --tp 8 \ --tool-call-parser glm47 \ --reasoning-parser glm45 \ @@ -120,7 +120,7 @@ The following ROCm command is an additional option for AMD GPUs and does not rep ```shell Command sglang serve \ - --model zai-org/GLM-5 \ + --model-path zai-org/GLM-5 \ --tp 8 \ --trust-remote-code \ --nsa-prefill-backend tilelang \ diff --git a/docs_new/src/snippets/autoregressive/deepseek-v32-deployment.jsx b/docs_new/src/snippets/autoregressive/deepseek-v32-deployment.jsx index 870e5d1df..641afd385 100644 --- a/docs_new/src/snippets/autoregressive/deepseek-v32-deployment.jsx +++ b/docs_new/src/snippets/autoregressive/deepseek-v32-deployment.jsx @@ -174,7 +174,7 @@ export const DeepSeekV32Deployment = () => { // NVFP4: fixed config if (isNvfp4) { let cmd = 'sglang serve \\\n'; - cmd += ` --model ${modelName}`; + cmd += ` --model-path ${modelName}`; cmd += ' \\\n --tp 4'; cmd += ' \\\n --quantization modelopt_fp4'; cmd += ' \\\n --moe-runner-backend flashinfer_trtllm'; @@ -184,14 +184,14 @@ export const DeepSeekV32Deployment = () => { // MXFP4: fixed config for AMD if (isMxfp4) { let cmd = 'sglang serve \\\n'; - cmd += ` --model ${modelName}`; + cmd += ` --model-path ${modelName}`; cmd += ' \\\n --tp 8'; cmd += ' \\\n --trust-remote-code'; return cmd; } let cmd = 'sglang serve \\\n'; - cmd += ` --model ${modelName}`; + cmd += ` --model-path ${modelName}`; // Hardware platform specific parameters if (isAMD) { diff --git a/docs_new/src/snippets/autoregressive/glm-5-deployment.jsx b/docs_new/src/snippets/autoregressive/glm-5-deployment.jsx index 1a7c8f274..26f1931ad 100644 --- a/docs_new/src/snippets/autoregressive/glm-5-deployment.jsx +++ b/docs_new/src/snippets/autoregressive/glm-5-deployment.jsx @@ -152,7 +152,7 @@ export const GLM5Deployment = () => { const memFraction = hwConfig.mem; let cmd = 'sglang serve \\\n'; - cmd += ` --model ${modelName}`; + cmd += ` --model-path ${modelName}`; cmd += ` \\\n --tp ${tpValue}`; // NVFP4 B200: trtllm NSA backends, flashinfer fusion, FP8 KV cache. diff --git a/docs_new/src/snippets/autoregressive/ministral-3-deployment.jsx b/docs_new/src/snippets/autoregressive/ministral-3-deployment.jsx index 94f007ab5..8092c8e70 100644 --- a/docs_new/src/snippets/autoregressive/ministral-3-deployment.jsx +++ b/docs_new/src/snippets/autoregressive/ministral-3-deployment.jsx @@ -50,7 +50,7 @@ export const Ministral3Deployment = () => { let cmd = 'sglang serve \\\n'; - cmd += ` --model ${modelCfg.modelId}`; + cmd += ` --model-path ${modelCfg.modelId}`; if (tp > 1) { cmd += ` \\\n --tp ${tp}`;