Update README.md

README.md

@@ -16,7 +16,20 @@ Check the original model card for information about this model.
 
 # Running the model with VLLM in Docker
 ```sh
-sudo docker run --runtime nvidia --gpus all -p 8000:8000 --ipc=host stepfun2025/vllm:step-audio-2-v20250909 --model Firworks/Step-Audio-R1-nvfp4 --dtype auto --max-model-len 32768
+docker run --rm -ti --gpus all \
+    -v $(pwd)/Step-Audio-R1:/Step-Audio-R1 \
+    -p 9999:9999 \
+    stepfun2025/vllm:step-audio-2-v20250909 \
+    -- vllm serve /Step-Audio-R1 \
+    --served-model-name Step-Audio-R1 \
+    --port 9999 \
+    --max-model-len 16384 \
+    --max-num-seqs 32 \
+    --tensor-parallel-size 4 \
+    --chat-template '{%- macro render_content(content) -%}{%- if content is string -%}{{- content.replace("<audio_patch>\n", "<audio_patch>") -}}{%- elif content is mapping -%}{{- content['"'"'value'"'"'] if '"'"'value'"'"' in content else content['"'"'text'"'"'] -}}{%- elif content is iterable -%}{%- for item in content -%}{%- if item.type == '"'"'text'"'"' -%}{{- item['"'"'value'"'"'] if '"'"'value'"'"' in item else item['"'"'text'"'"'] -}}{%- elif item.type == '"'"'audio'"'"' -%}<audio_patch>{%- endif -%}{%- endfor -%}{%- endif -%}{%- endmacro -%}{%- if tools -%}{{- '"'"'<|BOT|>system\n'"'"' -}}{%- if messages[0]['"'"'role'"'"'] == '"'"'system'"'"' -%}{{- render_content(messages[0]['"'"'content'"'"']) + '"'"'<|EOT|>'"'"' -}}{%- endif -%}{{- '"'"'<|BOT|>tool_json_schemas\n'"'"' + tools|tojson + '"'"'<|EOT|>'"'"' -}}{%- else -%}{%- if messages[0]['"'"'role'"'"'] == '"'"'system'"'"' -%}{{- '"'"'<|BOT|>system\n'"'"' + render_content(messages[0]['"'"'content'"'"']) + '"'"'<|EOT|>'"'"' -}}{%- endif -%}{%- endif -%}{%- for message in messages -%}{%- if message["role"] == "user" -%}{{- '"'"'<|BOT|>human\n'"'"' + render_content(message["content"]) + '"'"'<|EOT|>'"'"' -}}{%- elif message["role"] == "assistant" -%}{{- '"'"'<|BOT|>assistant\n'"'"' + (render_content(message["content"]) if message["content"] else '"'"''"'"') -}}{%- set is_last_assistant = true -%}{%- for m in messages[loop.index:] -%}{%- if m["role"] == "assistant" -%}{%- set is_last_assistant = false -%}{%- endif -%}{%- endfor -%}{%- if not is_last_assistant -%}{{- '"'"'<|EOT|>'"'"' -}}{%- endif -%}{%- elif message["role"] == "function_output" -%}{%- else -%}{%- if not (loop.first and message["role"] == "system") -%}{{- '"'"'<|BOT|>'"'"' + message["role"] + '"'"'\n'"'"' + render_content(message["content"]) + '"'"'<|EOT|>'"'"' -}}{%- endif -%}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{- '"'"'<|BOT|>assistant\n<think>\n'"'"' -}}{%- endif -%}' \
+    --enable-log-requests \
+    --interleave-mm-strings \
+    --trust-remote-code
 ```
 This was tested on an RTX Pro 6000 Blackwell cloud instance.