Update hub.json

Update tests.json
Create tests.json
2025-03-31 15:55:35 -07:00 · 2025-03-31 15:49:31 -07:00 · 2025-03-31 15:32:06 -07:00 · 2025-03-31 15:14:40 -07:00 · 2025-03-31 15:14:24 -07:00 · 2025-03-26 15:56:04 -07:00
6 changed files with 1216 additions and 21 deletions
@@ -0,0 +1,44 @@
+{
+  "tests": [
+    {
+      "name": "basic_inference_test",
+      "input": {
+        "prompt": "Write a short poem about artificial intelligence.",
+      },
+      "timeout": 30000
+    }
+  ],
+  "config": {
+    "gpuTypeId": "NVIDIA GeForce RTX 4090",
+    "gpuCount": 1,
+    "env": [
+      {
+        "key": "MODEL_NAME",
+        "value": "facebook/opt-350m"
+      },
+      {
+        "key": "HF_TOKEN",
+        "value": "hf_dummy_token_for_testing_purposes_only"
+      },
+      {
+        "key": "MAX_MODEL_LEN",
+        "value": "8192"
+      },
+      {
+        "key": "GPU_MEMORY_UTILIZATION",
+        "value": "0.95"
+      }
+    ],
+    "allowedCudaVersions": [
+      "12.7", 
+      "12.6", 
+      "12.5", 
+      "12.4", 
+      "12.3", 
+      "12.2", 
+      "12.1", 
+      "12.0", 
+      "11.7"
+    ]
+  }
+}
@@ -12,7 +12,7 @@ RUN --mount=type=cache,target=/root/.cache/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 
-RUN python3 -m pip install vllm==0.7.3 && \
+RUN python3 -m pip install vllm==0.8.2 && \
    python3 -m pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3

 # Setup for Option 2: Building the Image with the Model included
@@ -18,9 +18,9 @@ Deploy OpenAI-Compatible Blazing-Fast LLM Endpoints powered by the [vLLM](https:
 ### 1. UI for Deploying vLLM Worker on RunPod console:
 ![Demo of Deploying vLLM Worker on RunPod console with new UI](media/ui_demo.gif)

-### 2. Worker vLLM `v2.1.0` with vLLM `0.7.3` now available under `stable` tags 
+### 2. Worker vLLM `v2.2.0` with vLLM `0.8.2` now available under `stable` tags 

-Update v2.0.0 is now available, use the image tag `runpod/worker-v1-vllm:v2.1.0stable-cuda12.1.0`.
+Update v2.2.0 is now available, use the image tag `runpod/worker-v1-vllm:v2.2.0stable-cuda12.1.0`.

 ### 3. OpenAI-Compatible [Embedding Worker](https://github.com/runpod-workers/worker-infinity-embedding) Released
 Deploy your own OpenAI-compatible Serverless Endpoint on RunPod with multiple embedding models and fast inference for RAG and more! 
@@ -82,7 +82,7 @@ Below is a summary of the available RunPod Worker images, categorized by image s

 | CUDA Version | Stable Image Tag                  | Development Image Tag             | Note                                                        |
 |--------------|-----------------------------------|-----------------------------------|----------------------------------------------------------------------|
-| 12.1.0       | `runpod/worker-v1-vllm:v2.1.0stable-cuda12.1.0` | `runpod/worker-v1-vllm:v2.1.0dev-cuda12.1.0` | When creating an Endpoint, select CUDA Version 12.3, 12.2 and 12.1 in the filter. |
+| 12.1.0       | `runpod/worker-v1-vllm:v2.2.0stable-cuda12.1.0` | `runpod/worker-v1-vllm:v2.2.0dev-cuda12.1.0` | When creating an Endpoint, select CUDA Version 12.3, 12.2 and 12.1 in the filter. |



@@ -488,7 +488,15 @@ The prompt string can be any string, and the model's chat template will not be a

    Example:
    ```json
-    "prompt": "..."
+    {
+      "input": {
+        "prompt": "why sky is blue?",
+        "sampling_params": {
+          "temperature": 0.7,
+          "max_tokens": 100
+        }
+      }
+    }
    ```
 2. `messages`
 Your list can contain any number of messages, and each message usually can have any role from the following list:
@@ -502,20 +510,28 @@ Your list can contain any number of messages, and each message usually can have

    Example:
    ```json
-    "messages": [
-        {
-          "role": "system",
-          "content": "..."
-        },
-        {
-          "role": "user",
-          "content": "..."
-        },
-        {
-          "role": "assistant",
-          "content": "..."
+    {
+      "input": {
+        "messages": [
+          {
+            "role": "system",
+            "content": "You are a helpful AI assistant that provides clear and concise responses."
+          },
+          {
+            "role": "user",
+            "content": "Can you explain the difference between supervised and unsupervised learning?"
+          },
+          {
+            "role": "assistant",
+            "content": "Sure! Supervised learning uses labeled data, meaning each input has a corresponding correct output. The model learns by mapping inputs to known outputs. In contrast, unsupervised learning works with unlabeled data, where the model identifies patterns, structures, or clusters without predefined answers."
+          }
+        ],
+        "sampling_params": {
+          "temperature": 0.7,
+          "max_tokens": 100
        }
-      ]
+      }
+    }
    ```

 </details>
@@ -1,7 +1,7 @@
 ray
 pandas
 pyarrow
-runpod~=1.7.0
+runpod~=1.7.7
 huggingface-hub
 packaging
 typing-extensions==4.7.1
@@ -1,7 +1,68 @@
 {
  "versions": {
-    "0.7.0": {
-      "imageName": "runpod/worker-v1-vllm:v1.9.0stable-cuda12.1.0",
+    "0.8.2": {
+      "imageName": "runpod/worker-v1-vllm:v2.2.0stable-cuda12.1.0",
+      "minimumCudaVersion": "12.1",
+      "categories": [
+        {
+          "title": "LLM Settings",
+          "settings": [
+            "TOKENIZER", "TOKENIZER_MODE", "SKIP_TOKENIZER_INIT", "TRUST_REMOTE_CODE",
+            "DOWNLOAD_DIR", "LOAD_FORMAT", "DTYPE", "KV_CACHE_DTYPE", "QUANTIZATION_PARAM_PATH",
+            "MAX_MODEL_LEN", "GUIDED_DECODING_BACKEND", "DISTRIBUTED_EXECUTOR_BACKEND",
+            "WORKER_USE_RAY", "RAY_WORKERS_USE_NSIGHT", "PIPELINE_PARALLEL_SIZE",
+            "TENSOR_PARALLEL_SIZE", "MAX_PARALLEL_LOADING_WORKERS", "ENABLE_PREFIX_CACHING",
+            "DISABLE_SLIDING_WINDOW", "NUM_LOOKAHEAD_SLOTS",
+            "SEED", "NUM_GPU_BLOCKS_OVERRIDE", "MAX_NUM_BATCHED_TOKENS", "MAX_NUM_SEQS",
+            "MAX_LOGPROBS", "DISABLE_LOG_STATS", "QUANTIZATION", "ROPE_SCALING", "ROPE_THETA",
+            "TOKENIZER_POOL_SIZE", "TOKENIZER_POOL_TYPE", "TOKENIZER_POOL_EXTRA_CONFIG",
+            "ENABLE_LORA", "MAX_LORAS", "MAX_LORA_RANK", "LORA_EXTRA_VOCAB_SIZE",
+            "LORA_DTYPE", "LONG_LORA_SCALING_FACTORS", "MAX_CPU_LORAS", "FULLY_SHARDED_LORAS",
+            "DEVICE", "SCHEDULER_DELAY_FACTOR", "ENABLE_CHUNKED_PREFILL", "SPECULATIVE_MODEL",
+            "NUM_SPECULATIVE_TOKENS", "SPECULATIVE_DRAFT_TENSOR_PARALLEL_SIZE",
+            "SPECULATIVE_MAX_MODEL_LEN", "SPECULATIVE_DISABLE_BY_BATCH_SIZE",
+            "NGRAM_PROMPT_LOOKUP_MAX", "NGRAM_PROMPT_LOOKUP_MIN", "SPEC_DECODING_ACCEPTANCE_METHOD",
+            "TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_THRESHOLD", "TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_ALPHA",
+            "MODEL_LOADER_EXTRA_CONFIG", "PREEMPTION_MODE", "PREEMPTION_CHECK_PERIOD",
+            "PREEMPTION_CPU_CAPACITY", "MAX_LOG_LEN", "DISABLE_LOGGING_REQUEST",
+            "ENABLE_AUTO_TOOL_CHOICE", "TOOL_CALL_PARSER"
+          ]
+        },
+        {
+          "title": "Tokenizer Settings",
+          "settings": [
+            "TOKENIZER_NAME", "TOKENIZER_REVISION", "CUSTOM_CHAT_TEMPLATE"
+          ]
+        },
+        {
+          "title": "System Settings",
+          "settings": [
+            "GPU_MEMORY_UTILIZATION", "MAX_PARALLEL_LOADING_WORKERS", "BLOCK_SIZE",
+            "SWAP_SPACE", "ENFORCE_EAGER", "MAX_SEQ_LEN_TO_CAPTURE", "DISABLE_CUSTOM_ALL_REDUCE"
+          ]
+        },
+        {
+          "title": "Streaming Settings",
+          "settings": [
+            "DEFAULT_BATCH_SIZE", "DEFAULT_MIN_BATCH_SIZE", "DEFAULT_BATCH_SIZE_GROWTH_FACTOR"
+          ]
+        },
+        {
+          "title": "OpenAI Settings",
+          "settings": [
+            "RAW_OPENAI_OUTPUT", "OPENAI_RESPONSE_ROLE", "OPENAI_SERVED_MODEL_NAME_OVERRIDE"
+          ]
+        },
+        {
+          "title": "Serverless Settings",
+          "settings": [
+            "MAX_CONCURRENCY", "DISABLE_LOG_STATS", "DISABLE_LOG_REQUESTS"
+          ]
+        }
+      ]
+    },
+    "0.7.3": {
+      "imageName": "runpod/worker-v1-vllm:v2.1.0stable-cuda12.1.0",
      "minimumCudaVersion": "12.1",
      "categories": [
        {
@@ -122,6 +183,67 @@
        }
      ]
    },
+    "0.7.0": {
+      "imageName": "runpod/worker-v1-vllm:v1.9.0stable-cuda12.1.0",
+      "minimumCudaVersion": "12.1",
+      "categories": [
+        {
+          "title": "LLM Settings",
+          "settings": [
+            "TOKENIZER", "TOKENIZER_MODE", "SKIP_TOKENIZER_INIT", "TRUST_REMOTE_CODE",
+            "DOWNLOAD_DIR", "LOAD_FORMAT", "DTYPE", "KV_CACHE_DTYPE", "QUANTIZATION_PARAM_PATH",
+            "MAX_MODEL_LEN", "GUIDED_DECODING_BACKEND", "DISTRIBUTED_EXECUTOR_BACKEND",
+            "WORKER_USE_RAY", "RAY_WORKERS_USE_NSIGHT", "PIPELINE_PARALLEL_SIZE",
+            "TENSOR_PARALLEL_SIZE", "MAX_PARALLEL_LOADING_WORKERS", "ENABLE_PREFIX_CACHING",
+            "DISABLE_SLIDING_WINDOW", "NUM_LOOKAHEAD_SLOTS",
+            "SEED", "NUM_GPU_BLOCKS_OVERRIDE", "MAX_NUM_BATCHED_TOKENS", "MAX_NUM_SEQS",
+            "MAX_LOGPROBS", "DISABLE_LOG_STATS", "QUANTIZATION", "ROPE_SCALING", "ROPE_THETA",
+            "TOKENIZER_POOL_SIZE", "TOKENIZER_POOL_TYPE", "TOKENIZER_POOL_EXTRA_CONFIG",
+            "ENABLE_LORA", "MAX_LORAS", "MAX_LORA_RANK", "LORA_EXTRA_VOCAB_SIZE",
+            "LORA_DTYPE", "LONG_LORA_SCALING_FACTORS", "MAX_CPU_LORAS", "FULLY_SHARDED_LORAS",
+            "DEVICE", "SCHEDULER_DELAY_FACTOR", "ENABLE_CHUNKED_PREFILL", "SPECULATIVE_MODEL",
+            "NUM_SPECULATIVE_TOKENS", "SPECULATIVE_DRAFT_TENSOR_PARALLEL_SIZE",
+            "SPECULATIVE_MAX_MODEL_LEN", "SPECULATIVE_DISABLE_BY_BATCH_SIZE",
+            "NGRAM_PROMPT_LOOKUP_MAX", "NGRAM_PROMPT_LOOKUP_MIN", "SPEC_DECODING_ACCEPTANCE_METHOD",
+            "TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_THRESHOLD", "TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_ALPHA",
+            "MODEL_LOADER_EXTRA_CONFIG", "PREEMPTION_MODE", "PREEMPTION_CHECK_PERIOD",
+            "PREEMPTION_CPU_CAPACITY", "MAX_LOG_LEN", "DISABLE_LOGGING_REQUEST",
+            "ENABLE_AUTO_TOOL_CHOICE", "TOOL_CALL_PARSER"
+          ]
+        },
+        {
+          "title": "Tokenizer Settings",
+          "settings": [
+            "TOKENIZER_NAME", "TOKENIZER_REVISION", "CUSTOM_CHAT_TEMPLATE"
+          ]
+        },
+        {
+          "title": "System Settings",
+          "settings": [
+            "GPU_MEMORY_UTILIZATION", "MAX_PARALLEL_LOADING_WORKERS", "BLOCK_SIZE",
+            "SWAP_SPACE", "ENFORCE_EAGER", "MAX_SEQ_LEN_TO_CAPTURE", "DISABLE_CUSTOM_ALL_REDUCE"
+          ]
+        },
+        {
+          "title": "Streaming Settings",
+          "settings": [
+            "DEFAULT_BATCH_SIZE", "DEFAULT_MIN_BATCH_SIZE", "DEFAULT_BATCH_SIZE_GROWTH_FACTOR"
+          ]
+        },
+        {
+          "title": "OpenAI Settings",
+          "settings": [
+            "RAW_OPENAI_OUTPUT", "OPENAI_RESPONSE_ROLE", "OPENAI_SERVED_MODEL_NAME_OVERRIDE"
+          ]
+        },
+        {
+          "title": "Serverless Settings",
+          "settings": [
+            "MAX_CONCURRENCY", "DISABLE_LOG_STATS", "DISABLE_LOG_REQUESTS"
+          ]
+        }
+      ]
+    },
    "0.6.4": {
      "imageName": "runpod/worker-v1-vllm:v1.7.0stable-cuda12.1.0",
      "minimumCudaVersion": "12.1",
Author	SHA1	Message	Date
Marut PandyaandGitHub	5864fa6843	Update hub.json	2025-03-31 15:55:35 -07:00
Marut PandyaandGitHub	067f0bc173	Update tests.json	2025-03-31 15:49:31 -07:00
Marut PandyaandGitHub	0869068e7c	Create tests.json	2025-03-31 15:32:06 -07:00
Marut PandyaandGitHub	19f25b17de	Update hub.json	2025-03-31 15:14:40 -07:00
Marut PandyaandGitHub	70aa748c30	Update hub.json	2025-03-31 15:14:24 -07:00
Marut PandyaandGitHub	da3e5f524b	Merge pull request #171 from runpod-workers/update update vllm 0.8.2	2025-03-26 15:56:04 -07:00
pandyamarut	acbdf63de8	update vllm 0.8.2 Signed-off-by: pandyamarut <pandyamarut@gmail.com>	2025-03-26 15:55:30 -07:00
Hailong YangandGitHub	fa31d9663d	Update README.md	2025-03-11 22:24:22 -04:00
Marut PandyaandGitHub	b8fb313483	Merge pull request #168 from runpod-workers/wc-up update worker config	2025-03-11 12:23:22 -07:00
pandyamarut	9635daf336	update worker config Signed-off-by: pandyamarut <pandyamarut@gmail.com>	2025-03-11 12:22:53 -07:00
Marut PandyaandGitHub	fb4e700090	Merge pull request #166 from KAJdev/patch-1 Create hub.json	2025-03-10 12:14:47 -07:00
Marut PandyaandGitHub	d4872ed9c8	Merge pull request #167 from runpod-workers/rachfop-patch-1 Update requirements.txt	2025-03-10 12:13:47 -07:00
Patrick RachfordandGitHub	b2eef50c3b	Update requirements.txt Use the latest runpod version from here: https://github.com/runpod/runpod-python/releases/tag/1.7.7	2025-03-10 08:46:28 -07:00
Ezekiel WotringandGitHub	8005bcc1a8	fix description	2025-03-07 13:22:34 -09:00
Ezekiel WotringandGitHub	aa7b00ddda	Create hub.json	2025-03-07 13:20:52 -09:00