fix: deactivate RunPod tests to fix hub release (#253)

Rename tests.json to tests_json to temporarily disable automated
tests while fixing the release on the hub.

.runpod/README.md

@@ -1,260 +1,261 @@
-![vLLM worker banner](https://cpjrphpz3t5wbwfe.public.blob.vercel-storage.com/worker-vllm_banner.jpeg)
+![vLLM worker banner](https://cpjrphpz3t5wbwfe.public.blob.vercel-storage.com/worker-vllm_banner.jpeg)
-
+
-Run LLMs using [vLLM](https://docs.vllm.ai) with an OpenAI-compatible API
+Run LLMs using [vLLM](https://docs.vllm.ai) with an OpenAI-compatible API
-
+
----
+---
-
+
-[![RunPod](https://api.runpod.io/badge/runpod-workers/worker-vllm)](https://www.runpod.io/console/hub/runpod-workers/worker-vllm)
+[![RunPod](https://api.runpod.io/badge/runpod-workers/worker-vllm)](https://www.runpod.io/console/hub/runpod-workers/worker-vllm)
-
+
----
+---
-
+
-## Endpoint Configuration
+## Endpoint Configuration
-
+
-All behaviour is controlled through environment variables:
+All behaviour is controlled through environment variables:
-
+
-| Environment Variable                | Description                                       | Default             | Options                                                            |
+| Environment Variable                | Description                                       | Default             | Options                                                            |
-| ----------------------------------- | ------------------------------------------------- | ------------------- | ------------------------------------------------------------------ |
+| ----------------------------------- | ------------------------------------------------- | ------------------- | ------------------------------------------------------------------ |
-| `MODEL_NAME`                        | Path of the model weights                         | "facebook/opt-125m" | Local folder or Hugging Face repo ID                               |
+| `MODEL_NAME`                        | Path of the model weights                         | "facebook/opt-125m" | Local folder or Hugging Face repo ID                               |
-| `HF_TOKEN`                          | HuggingFace access token for gated/private models |                     | Your HuggingFace access token                                      |
+| `HF_TOKEN`                          | HuggingFace access token for gated/private models |                     | Your HuggingFace access token                                      |
-| `MAX_MODEL_LEN`                     | Model's maximum context length                    |                     | Integer (e.g., 4096)                                               |
+| `MAX_MODEL_LEN`                     | Model's maximum context length                    |                     | Integer (e.g., 4096)                                               |
-| `QUANTIZATION`                      | Quantization method                               |                     | "awq", "gptq", "squeezellm", "bitsandbytes"                        |
+| `QUANTIZATION`                      | Quantization method                               |                     | "awq", "gptq", "squeezellm", "bitsandbytes"                        |
-| `TENSOR_PARALLEL_SIZE`              | Number of GPUs                                    | 1                   | Integer                                                            |
+| `TENSOR_PARALLEL_SIZE`              | Number of GPUs                                    | 1                   | Integer                                                            |
-| `GPU_MEMORY_UTILIZATION`            | Fraction of GPU memory to use                     | 0.95                | Float between 0.0 and 1.0                                          |
+| `GPU_MEMORY_UTILIZATION`            | Fraction of GPU memory to use                     | 0.95                | Float between 0.0 and 1.0                                          |
-| `MAX_NUM_SEQS`                      | Maximum number of sequences per iteration         | 256                 | Integer                                                            |
+| `MAX_NUM_SEQS`                      | Maximum number of sequences per iteration         | 256                 | Integer                                                            |
-| `CUSTOM_CHAT_TEMPLATE`              | Custom chat template override                     |                     | Jinja2 template string                                             |
+| `CUSTOM_CHAT_TEMPLATE`              | Custom chat template override                     |                     | Jinja2 template string                                             |
-| `ENABLE_AUTO_TOOL_CHOICE`           | Enable automatic tool selection                   | false               | boolean (true or false)                                            |
+| `ENABLE_AUTO_TOOL_CHOICE`           | Enable automatic tool selection                   | false               | boolean (true or false)                                            |
-| `TOOL_CALL_PARSER`                  | Parser for tool calls                             |                     | "mistral", "hermes", "llama3_json", "granite", "deepseek_v3", etc. |
+| `TOOL_CALL_PARSER`                  | Parser for tool calls                             |                     | "mistral", "hermes", "llama3_json", "granite", "deepseek_v3", etc. |
-| `OPENAI_SERVED_MODEL_NAME_OVERRIDE` | Override served model name in API                 |                     | String                                                             |
+| `REASONING_PARSER`                  | Parser for reasoning-capable models               |                     | "deepseek_r1", "qwen3", "granite", "hunyuan_a13b"                  |
-| `MAX_CONCURRENCY`                   | Maximum concurrent requests                       | 300                 | Integer                                                            |
+| `OPENAI_SERVED_MODEL_NAME_OVERRIDE` | Override served model name in API                 |                     | String                                                             |
-
+| `MAX_CONCURRENCY`                   | Maximum concurrent requests                       | 300                 | Integer                                                            |
-For complete configuration options, see the [full configuration documentation](https://github.com/runpod-workers/worker-vllm/blob/main/docs/configuration.md).
+
-
+For complete configuration options, see the [full configuration documentation](https://github.com/runpod-workers/worker-vllm/blob/main/docs/configuration.md).
-## API Usage
+
-
+## API Usage
-This worker supports two API formats: **RunPod native** and **OpenAI-compatible**.
+
-
+This worker supports two API formats: **RunPod native** and **OpenAI-compatible**.
-### RunPod Native API
+
-
+### RunPod Native API
-For testing directly in the RunPod UI, use these examples in your endpoint's request tab.
+
-
+For testing directly in the RunPod UI, use these examples in your endpoint's request tab.
-#### Chat Completions
+
-
+#### Chat Completions
-```json
+
-{
+```json
-  "input": {
+{
-    "messages": [
+  "input": {
-      { "role": "system", "content": "You are a helpful assistant." },
+    "messages": [
-      { "role": "user", "content": "What is the capital of France?" }
+      { "role": "system", "content": "You are a helpful assistant." },
-    ],
+      { "role": "user", "content": "What is the capital of France?" }
-    "sampling_params": {
+    ],
-      "max_tokens": 100,
+    "sampling_params": {
-      "temperature": 0.7
+      "max_tokens": 100,
-    }
+      "temperature": 0.7
-  }
+    }
-}
+  }
-```
+}
-
+```
-#### Chat Completions (Streaming)
+
-
+#### Chat Completions (Streaming)
-```json
+
-{
+```json
-  "input": {
+{
-    "messages": [
+  "input": {
-      { "role": "user", "content": "Write a short story about a robot." }
+    "messages": [
-    ],
+      { "role": "user", "content": "Write a short story about a robot." }
-    "sampling_params": {
+    ],
-      "max_tokens": 500,
+    "sampling_params": {
-      "temperature": 0.8
+      "max_tokens": 500,
-    },
+      "temperature": 0.8
-    "stream": true
+    },
-  }
+    "stream": true
-}
+  }
-```
+}
-
+```
-#### Text Generation
+
-
+#### Text Generation
-For direct text generation without chat format:
+
-
+For direct text generation without chat format:
-```json
+
-{
+```json
-  "input": {
+{
-    "prompt": "The capital of France is",
+  "input": {
-    "sampling_params": {
+    "prompt": "The capital of France is",
-      "max_tokens": 64,
+    "sampling_params": {
-      "temperature": 0.0
+      "max_tokens": 64,
-    }
+      "temperature": 0.0
-  }
+    }
-}
+  }
-```
+}
-
+```
-#### List Models
+
-
+#### List Models
-```json
+
-{
+```json
-  "input": {
+{
-    "openai_route": "/v1/models"
+  "input": {
-  }
+    "openai_route": "/v1/models"
-}
+  }
-```
+}
-
+```
----
+
-
+---
-### OpenAI-Compatible API
+
-
+### OpenAI-Compatible API
-For external clients and SDKs, use the `/openai/v1` path prefix with your RunPod API key.
+
-
+For external clients and SDKs, use the `/openai/v1` path prefix with your RunPod API key.
-#### Chat Completions
+
-
+#### Chat Completions
-**Path:** `/openai/v1/chat/completions`
+
-
+**Path:** `/openai/v1/chat/completions`
-```json
+
-{
+```json
-  "model": "meta-llama/Llama-2-7b-chat-hf",
+{
-  "messages": [
+  "model": "meta-llama/Llama-2-7b-chat-hf",
-    { "role": "system", "content": "You are a helpful assistant." },
+  "messages": [
-    { "role": "user", "content": "What is the capital of France?" }
+    { "role": "system", "content": "You are a helpful assistant." },
-  ],
+    { "role": "user", "content": "What is the capital of France?" }
-  "max_tokens": 100,
+  ],
-  "temperature": 0.7
+  "max_tokens": 100,
-}
+  "temperature": 0.7
-```
+}
-
+```
-#### Chat Completions (Streaming)
+
-
+#### Chat Completions (Streaming)
-```json
+
-{
+```json
-  "model": "meta-llama/Llama-2-7b-chat-hf",
+{
-  "messages": [
+  "model": "meta-llama/Llama-2-7b-chat-hf",
-    { "role": "user", "content": "Write a short story about a robot." }
+  "messages": [
-  ],
+    { "role": "user", "content": "Write a short story about a robot." }
-  "max_tokens": 500,
+  ],
-  "temperature": 0.8,
+  "max_tokens": 500,
-  "stream": true
+  "temperature": 0.8,
-}
+  "stream": true
-```
+}
-
+```
-#### Text Completions
+
-
+#### Text Completions
-**Path:** `/openai/v1/completions`
+
-
+**Path:** `/openai/v1/completions`
-```json
+
-{
+```json
-  "model": "meta-llama/Llama-2-7b-chat-hf",
+{
-  "prompt": "The capital of France is",
+  "model": "meta-llama/Llama-2-7b-chat-hf",
-  "max_tokens": 100,
+  "prompt": "The capital of France is",
-  "temperature": 0.7
+  "max_tokens": 100,
-}
+  "temperature": 0.7
-```
+}
-
+```
-#### List Models
+
-
+#### List Models
-**Path:** `/openai/v1/models`
+
-
+**Path:** `/openai/v1/models`
-```json
+
-{}
+```json
-```
+{}
-
+```
-#### Response Format
+
-
+#### Response Format
-Both APIs return the same response format:
+
-
+Both APIs return the same response format:
-```json
+
-{
+```json
-  "choices": [
+{
-    {
+  "choices": [
-      "index": 0,
+    {
-      "message": { "role": "assistant", "content": "Paris." },
+      "index": 0,
-      "finish_reason": "stop"
+      "message": { "role": "assistant", "content": "Paris." },
-    }
+      "finish_reason": "stop"
-  ],
+    }
-  "usage": { "prompt_tokens": 9, "completion_tokens": 1, "total_tokens": 10 }
+  ],
-}
+  "usage": { "prompt_tokens": 9, "completion_tokens": 1, "total_tokens": 10 }
-```
+}
-
+```
----
+
-
+---
-## Usage
+
-
+## Usage
-Below are minimal `python` snippets so you can copy-paste to get started quickly.
+
-
+Below are minimal `python` snippets so you can copy-paste to get started quickly.
-> Replace `<ENDPOINT_ID>` with your endpoint ID and `<API_KEY>` with a [RunPod API key](https://docs.runpod.io/get-started/api-keys).
+
-
+> Replace `<ENDPOINT_ID>` with your endpoint ID and `<API_KEY>` with a [RunPod API key](https://docs.runpod.io/get-started/api-keys).
-### OpenAI compatible API
+
-
+### OpenAI compatible API
-Minimal Python example using the official `openai` SDK:
+
-
+Minimal Python example using the official `openai` SDK:
-```python
+
-from openai import OpenAI
+```python
-import os
+from openai import OpenAI
-
+import os
-# Initialize the OpenAI Client with your RunPod API Key and Endpoint URL
+
-client = OpenAI(
+# Initialize the OpenAI Client with your RunPod API Key and Endpoint URL
-    api_key=os.getenv("RUNPOD_API_KEY"),
+client = OpenAI(
-    base_url=f"https://api.runpod.ai/v2/<ENDPOINT_ID>/openai/v1",
+    api_key=os.getenv("RUNPOD_API_KEY"),
-)
+    base_url=f"https://api.runpod.ai/v2/<ENDPOINT_ID>/openai/v1",
-```
+)
-
+```
-`Chat Completions (Non-Streaming)`
+
-
+`Chat Completions (Non-Streaming)`
-```python
+
-response = client.chat.completions.create(
+```python
-    model="meta-llama/Llama-2-7b-chat-hf",
+response = client.chat.completions.create(
-    messages=[{"role": "user", "content": "Explain quantum computing in simple terms"}],
+    model="meta-llama/Llama-2-7b-chat-hf",
-    temperature=0,
+    messages=[{"role": "user", "content": "Explain quantum computing in simple terms"}],
-    max_tokens=100,
+    temperature=0,
-)
+    max_tokens=100,
-print(f"Response: {response.choices[0].message.content}")
+)
-```
+print(f"Response: {response.choices[0].message.content}")
-
+```
-`Chat Completions (Streaming)`
+
-
+`Chat Completions (Streaming)`
-```python
+
-response_stream = client.chat.completions.create(
+```python
-    model="meta-llama/Llama-2-7b-chat-hf",
+response_stream = client.chat.completions.create(
-    messages=[{"role": "user", "content": "Explain quantum computing in simple terms"}],
+    model="meta-llama/Llama-2-7b-chat-hf",
-    temperature=0,
+    messages=[{"role": "user", "content": "Explain quantum computing in simple terms"}],
-    max_tokens=100,
+    temperature=0,
-    stream=True
+    max_tokens=100,
-)
+    stream=True
-for response in response_stream:
+)
-    print(response.choices[0].delta.content or "", end="", flush=True)
+for response in response_stream:
-```
+    print(response.choices[0].delta.content or "", end="", flush=True)
-
+```
-### RunPod Native API
+
-
+### RunPod Native API
-```python
+
-import requests
+```python
-
+import requests
-response = requests.post(
+
-    "https://api.runpod.ai/v2/<ENDPOINT_ID>/run",
+response = requests.post(
-    headers={"Authorization": "Bearer <API_KEY>"},
+    "https://api.runpod.ai/v2/<ENDPOINT_ID>/run",
-    json={
+    headers={"Authorization": "Bearer <API_KEY>"},
-        "input": {
+    json={
-            "messages": [
+        "input": {
-                {"role": "system", "content": "You are a helpful assistant."},
+            "messages": [
-                {"role": "user", "content": "Explain quantum computing in simple terms"}
+                {"role": "system", "content": "You are a helpful assistant."},
-            ],
+                {"role": "user", "content": "Explain quantum computing in simple terms"}
-            "sampling_params": {
+            ],
-                "temperature": 0.7,
+            "sampling_params": {
-                "max_tokens": 150
+                "temperature": 0.7,
-            }
+                "max_tokens": 150
-        }
+            }
-    }
+        }
-)
+    }
-
+)
-result = response.json()
+
-print(result["output"])
+result = response.json()
-```
+print(result["output"])
-
+```
-## Compatibility
+
-
+## Compatibility
-For supported models, see the [vLLM supported models documentation](https://docs.vllm.ai/en/latest/models/supported_models.html).
+
-
+For supported models, see the [vLLM supported models documentation](https://docs.vllm.ai/en/latest/models/supported_models.html).
-Anything not recognized by worker-vllm is forwarded to vLLM's engine, so advanced options in the vLLM docs (guided generation, LoRA, speculative decoding, etc.) also work.
+
-
+Anything not recognized by worker-vllm is forwarded to vLLM's engine, so advanced options in the vLLM docs (guided generation, LoRA, speculative decoding, etc.) also work.
-## Documentation
+
-
+## Documentation
-- **[🚀 Deployment Guide](https://docs.runpod.io/serverless/vllm/get-started)** - Step-by-step setup
+
-- **[📖 Configuration Reference](https://github.com/runpod-workers/worker-vllm/blob/main/docs/configuration.md)** - All environment variables
+- **[🚀 Deployment Guide](https://docs.runpod.io/serverless/vllm/get-started)** - Step-by-step setup
-- **[🏗️ Advanced Deployment](https://github.com/runpod-workers/worker-vllm/blob/main/docs/deployment.md)** - Custom builds and strategies
+- **[📖 Configuration Reference](https://github.com/runpod-workers/worker-vllm/blob/main/docs/configuration.md)** - All environment variables
-- **[🔧 Development Guide](https://github.com/runpod-workers/worker-vllm/blob/main/docs/conventions.md)** - Architecture and patterns
+- **[🏗️ Advanced Deployment](https://github.com/runpod-workers/worker-vllm/blob/main/docs/deployment.md)** - Custom builds and strategies
+- **[🔧 Development Guide](https://github.com/runpod-workers/worker-vllm/blob/main/docs/conventions.md)** - Architecture and patterns

.runpod/hub.json

@@ -1,25 +1,15 @@
 {
   "title": "vLLM",
-  "description": "Deploy OpenAI-Compatible Blazing-Fast LLM Endpoints powered by the vLLM Inference Engine on RunPod Serverless",
+  "description": "Deploy OpenAI-Compatible Blazing-Fast LLM Endpoints powered by vLLM",
   "type": "serverless",
   "category": "language",
   "iconUrl": "https://registry.npmmirror.com/@lobehub/icons-static-png/latest/files/dark/vllm-color.png",
   "config": {
     "runsOn": "GPU",
-    "containerDiskInGb": 200,
+    "containerDiskInGb": 150,
-    "gpuIds": "ADA_80_PRO, AMPERE_80",
+    "gpuIds": "ADA_80_PRO,AMPERE_80",
     "gpuCount": 1,
-    "allowedCudaVersions": [
+    "allowedCudaVersions": ["12.9", "12.8", "12.7", "12.6", "12.5", "12.4"],
-      "12.9",
-      "12.8",
-      "12.7",
-      "12.6",
-      "12.5",
-      "12.4",
-      "12.3",
-      "12.2",
-      "12.1"
-    ],
     "presets": [
       {
         "name": "deepseek-ai/deepseek-r1-distill-llama-8b",
@@ -38,16 +28,6 @@
           "required": true
         }
       },
-      {
-        "key": "HF_TOKEN",
-        "input": {
-          "name": "Access Token",
-          "type": "string",
-          "description": "Hugging Face access token for gated & private models",
-          "default": "",
-          "required": false
-        }
-      },
       {
         "key": "TOKENIZER",
         "input": {
@@ -945,7 +925,17 @@
           "name": "Max Concurrency",
           "type": "number",
           "description": "Max concurrent requests per worker. vLLM has an internal queue, so you don't have to worry about limiting by VRAM, this is for improving scaling/load balancing efficiency",
-          "default": 300,
+          "default": 30,
+          "advanced": true
+        }
+      },
+      {
+        "key": "ENABLE_EXPERT_PARALLEL",
+        "input": {
+          "name": "Enable Expert Parallel",
+          "type": "boolean",
+          "description": "Enable Expert Parallel for MoE models",
+          "default": false,
           "advanced": true
         }
       },
@@ -1023,6 +1013,23 @@
           "default": "",
           "advanced": true
         }
+      },
+      {
+        "key": "REASONING_PARSER",
+        "input": {
+          "name": "Reasoning Parser",
+          "type": "string",
+          "description": "Parser for reasoning-capable models (enables reasoning mode)",
+          "options": [
+            { "label": "None", "value": "" },
+            { "label": "DeepSeek R1", "value": "deepseek_r1" },
+            { "label": "Qwen3", "value": "qwen3" },
+            { "label": "Granite", "value": "granite" },
+            { "label": "Hunyuan A13B", "value": "hunyuan_a13b" }
+          ],
+          "default": "",
+          "advanced": true
+        }
       }
     ]
   }

.runpod/tests_json

@@ -38,14 +38,6 @@
         "value": "HuggingFaceTB/SmolLM2-135M-Instruct"
       }
     ],
-    "allowedCudaVersions": [
+    "allowedCudaVersions": ["12.9", "12.8", "12.7", "12.6", "12.5"]
-      "12.7",
-      "12.6",
-      "12.5",
-      "12.4",
-      "12.3",
-      "12.2",
-      "12.1"
-    ]
   }
 }

Dockerfile

@@ -1,9 +1,9 @@
-FROM nvidia/cuda:12.1.0-base-ubuntu22.04 
+FROM nvidia/cuda:12.4.1-base-ubuntu22.04 
 
 RUN apt-get update -y \
     && apt-get install -y python3-pip
 
-RUN ldconfig /usr/local/cuda-12.1/compat/
+RUN ldconfig /usr/local/cuda-12.4/compat/
 
 # Install Python dependencies
 COPY builder/requirements.txt /requirements.txt
@@ -11,9 +11,8 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     python3 -m pip install --upgrade pip && \
     python3 -m pip install --upgrade -r /requirements.txt
 
-# Install vLLM (switching back to pip installs since issues that required building fork are fixed and space optimization is not as important since caching) and FlashInfer 
+# Install vLLM
-RUN python3 -m pip install vllm==0.10.0 && \
+RUN python3 -m pip install vllm==0.11.0
-    python3 -m pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3
 
 # Setup for Option 2: Building the Image with the Model included
 ARG MODEL_NAME=""

README.md

@@ -57,7 +57,7 @@ Configure worker-vllm using environment variables:
 | `ENABLE_AUTO_TOOL_CHOICE`           | Enable automatic tool selection                   | false               | boolean (true or false)                                            |
 | `TOOL_CALL_PARSER`                  | Parser for tool calls                             |                     | "mistral", "hermes", "llama3_json", "granite", "deepseek_v3", etc. |
 | `OPENAI_SERVED_MODEL_NAME_OVERRIDE` | Override served model name in API                 |                     | String                                                             |
-| `MAX_CONCURRENCY`                   | Maximum concurrent requests                       | 300                 | Integer                                                            |
+| `MAX_CONCURRENCY`                   | Maximum concurrent requests                       | 30                  | Integer                                                            |
 
 For the complete list of all available environment variables, examples, and detailed descriptions: **[Configuration](docs/configuration.md)**
 

builder/requirements.txt

@@ -1,14 +1,14 @@
 ray
 pandas
 pyarrow
-runpod~=1.7.7
+runpod>=1.8,<2.0
 huggingface-hub
 packaging
 typing-extensions>=4.8.0
 pydantic
 pydantic-settings
 hf-transfer
-transformers>=4.55.0
+transformers>=4.57.0
 bitsandbytes>=0.45.0
 kernels
 torch==2.6.0

docs/configuration.md

@@ -85,6 +85,7 @@ Complete guide to all environment variables and configuration options for worker
 | `ENFORCE_EAGER`                | False   | `bool`          | Always use eager-mode PyTorch. If False(`0`), will use eager mode and CUDA graph in hybrid for maximal performance and flexibility. |
 | `MAX_SEQ_LEN_TO_CAPTURE`       | `8192`  | `int`           | Maximum context length covered by CUDA graphs. When a sequence has context length larger than this, we fall back to eager mode.     |
 | `DISABLE_CUSTOM_ALL_REDUCE`    | `0`     | `int`           | Enables or disables custom all reduce.                                                                                              |
+| `ENABLE_EXPERT_PARALLEL`       | `False` | `bool`           |  Enable Expert Parallel for MoE models  |
 
 ## Tokenizer Settings
 
@@ -113,12 +114,13 @@ The way this works is that the first request will have a batch size of `DEFAULT_
 | `OPENAI_RESPONSE_ROLE`              | `assistant` | `str`            | Role of the LLM's Response in OpenAI Chat Completions.                                                                                                                                                            |
 | `ENABLE_AUTO_TOOL_CHOICE`           | `false`     | `bool`           | Enables automatic tool selection for supported models. Set to `true` to activate.                                                                                                                                 |
 | `TOOL_CALL_PARSER`                  | `None`      | `str`            | Specifies the parser for tool calls. Options: `mistral`, `hermes`, `llama3_json`, `llama4_json`, `llama4_pythonic`, `granite`, `granite-20b-fc`, `deepseek_v3`, `internlm`, `jamba`, `phi4_mini_json`, `pythonic` |
+| `REASONING_PARSER`                  | `None`      | `str`            | Parser for reasoning-capable models (enables reasoning mode). Examples: `deepseek_r1`, `qwen3`, `granite`, `hunyuan_a13b`. Leave unset to disable.                                                                |
 
 ## Serverless & Concurrency Settings
 
 | Variable               | Default | Type/Choices | Description                                                                                                                                                                |
 | ---------------------- | ------- | ------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `MAX_CONCURRENCY`      | `300`   | `int`        | Max concurrent requests per worker. vLLM has an internal queue, so you don't have to worry about limiting by VRAM, this is for improving scaling/load balancing efficiency |
+| `MAX_CONCURRENCY`      | `30`    | `int`        | Max concurrent requests per worker. vLLM has an internal queue, so you don't have to worry about limiting by VRAM, this is for improving scaling/load balancing efficiency |
 | `DISABLE_LOG_STATS`    | False   | `bool`       | Enables or disables vLLM stats logging.                                                                                                                                    |
 | `DISABLE_LOG_REQUESTS` | False   | `bool`       | Enables or disables vLLM request logging.                                                                                                                                  |
 

docs/conventions.md

@@ -51,7 +51,8 @@ RunPod Request → handler.py → JobInput → Engine Selection → vLLM Generat
 
 - `src/engine_args.py`: Centralized configuration management
 - `src/constants.py`: Default values for core settings
-- `worker-config.json`: UI form generation for RunPod console
+- `.runpod/hub.json`: Hub UI configuration (CRITICAL: always update when changing defaults)
+- `worker-config.json`: UI form generation for RunPod console (if exists)
 
 ## Core Development Concepts
 
@@ -222,7 +223,7 @@ src/
 
 ### 2. **Concurrency Patterns**
 
-- **Max Concurrency**: 300 concurrent requests by default
+- **Max Concurrency**: 30 concurrent requests by default
 - **vLLM Queuing**: Internal request batching and scheduling
 - **RunPod Integration**: Concurrency modifier for auto-scaling
 

src/constants.py

@@ -1,4 +1,4 @@
 DEFAULT_BATCH_SIZE = 50
-DEFAULT_MAX_CONCURRENCY = 300
+DEFAULT_MAX_CONCURRENCY = 30
 DEFAULT_BATCH_SIZE_GROWTH_FACTOR = 3
 DEFAULT_MIN_BATCH_SIZE = 1

src/engine_args.py

@@ -80,6 +80,7 @@ DEFAULT_ARGS = {
     "guided_decoding_backend": os.getenv('GUIDED_DECODING_BACKEND', 'outlines'),
     "speculative_model": os.getenv('SPECULATIVE_MODEL', None),
     "speculative_draft_tensor_parallel_size": int(os.getenv('SPECULATIVE_DRAFT_TENSOR_PARALLEL_SIZE', 0)) or None,
+    "enable_expert_parallel": bool(os.getenv('ENABLE_EXPERT_PARALLEL', 'False').lower() == 'true'),
     "num_speculative_tokens": int(os.getenv('NUM_SPECULATIVE_TOKENS', 0)) or None,
     "speculative_max_model_len": int(os.getenv('SPECULATIVE_MAX_MODEL_LEN', 0)) or None,
     "speculative_disable_by_batch_size": int(os.getenv('SPECULATIVE_DISABLE_BY_BATCH_SIZE', 0)) or None,