update worker-config

Signed-off-by: pandyamarut <pandyamarut@gmail.com>
update engine
2024-12-30 17:41:10 -08:00 · 2024-12-30 17:13:03 -08:00 · 2024-12-30 15:23:44 -08:00 · 2024-12-30 15:20:11 -08:00 · 2024-12-15 20:50:47 -08:00 · 2024-12-06 16:29:06 +01:00
4 changed files with 99 additions and 69 deletions
@@ -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==0.6.4 && \
+RUN python3 -m pip install vllm==0.6.6.post1 && \
    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 `v1.6.0` with vLLM `0.6.3` now available under `stable` tags 
+### 2. Worker vLLM `v1.8.0` with vLLM `0.6.6` now available under `stable` tags 

-Update v1.6.0 is now available, use the image tag `runpod/worker-v1-vllm:v1.6.0stable-cuda12.1.0`.
+Update v1.8.0 is now available, use the image tag `runpod/worker-v1-vllm:v1.8.0stable-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:v1.6.0stable-cuda12.1.0` | `runpod/worker-v1-vllm:v1.6.0dev-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:v1.8.0stable-cuda12.1.0` | `runpod/worker-v1-vllm:v1.8.0dev-cuda12.1.0` | When creating an Endpoint, select CUDA Version 12.3, 12.2 and 12.1 in the filter. |



@@ -146,8 +146,11 @@ class OpenAIvLLMEngine(vLLMEngine):
            base_model_paths=self.base_model_paths,
            response_role=self.response_role,
            chat_template=self.tokenizer.tokenizer.chat_template,
+            enable_auto_tools=os.getenv('ENABLE_AUTO_TOOL_CHOICE', 'false').lower() == 'true',
+            tool_parser=os.getenv('TOOL_CALL_PARSER', "") or None,
            lora_modules=lora_modules,
            prompt_adapters=None,
+            chat_template_content_format="auto",
            request_logger=None
        )
        self.completion_engine = OpenAIServingCompletion(
@@ -1,7 +1,7 @@
 {
  "versions": {
-    "0.6.4": {
-      "imageName": "runpod/worker-v1-vllm:v1.6.0stable-cuda12.1.0",
+    "0.6.6": {
+      "imageName": "runpod/worker-v1-vllm:v1.8.0stable-cuda12.1.0",
      "minimumCudaVersion": "12.1",
      "categories": [
        {
@@ -24,7 +24,69 @@
            "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"
+            "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",
+      "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"
          ]
        },
        {
@@ -84,7 +146,8 @@
            "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"
+            "PREEMPTION_CPU_CAPACITY", "MAX_LOG_LEN", "DISABLE_LOGGING_REQUEST",
+            "ENABLE_AUTO_TOOL_CHOICE", "TOOL_CALL_PARSER"
          ]
        },
        {
@@ -239,66 +302,6 @@
          ]
        }
      ]
-    },
-    "0.5.5": {
-      "imageName": "runpod/worker-v1-vllm:v1.3.1stable-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", "USE_V2_BLOCK_MANAGER", "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"
-          ]
-        },
-        {
-          "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"
-          ]
-        }
-      ]
    }
  },
  "schema": {
@@ -991,6 +994,30 @@
    "description": "Enables or disables vLLM request logging",
    "required": false,
    "type": "toggle"
+  },
+  "ENABLE_AUTO_TOOL_CHOICE": {
+    "env_var_name": "ENABLE_AUTO_TOOL_CHOICE",
+    "value": false,
+    "title": "Enable Auto Tool Choice",
+    "description": "Enables or disables auto tool choice",
+    "required": false,
+    "type": "toggle"
+  },
+  "TOOL_CALL_PARSER": {
+    "env_var_name": "TOOL_CALL_PARSER",
+    "value": "",
+    "title": "Tool Call Parser",
+    "description": "Tool call parser",
+    "required": false,
+    "type": "select",
+    "options": [
+      { "value": "", "label": "None" },
+      { "value": "hermes", "label": "Hermes" },
+      { "value": "mistral", "label": "Mistral" },
+      { "value": "llama3_json", "label": "Llama3 JSON" },
+      { "value": "pythonic", "label": "Pythonic" },
+      { "value": "internlm", "label": "InternLM" }
+    ]
  }
 }
 }
Author	SHA1	Message	Date
pandyamarut	8e3c26be14	update worker-config Signed-off-by: pandyamarut <pandyamarut@gmail.com>	2024-12-30 17:41:10 -08:00
pandyamarut	66ea8b1110	update engine Signed-off-by: pandyamarut <pandyamarut@gmail.com>	2024-12-30 17:13:03 -08:00
Marut PandyaandGitHub	a3d432afdf	Merge pull request #140 from runpod-workers/nw-updte upgrade vllm version	2024-12-30 15:23:44 -08:00
pandyamarut	06c2bb1715	upgrade vllm version Signed-off-by: pandyamarut <pandyamarut@gmail.com>	2024-12-30 15:20:11 -08:00
Marut PandyaandGitHub	d2e355eae9	Merge pull request #137 from kldzj/fix-tool-calling fix: openai tool calling	2024-12-15 20:50:47 -08:00
kldzj	b7787d8ca8	fix: remove unused import	2024-12-06 16:29:06 +01:00
kldzj	b1fca5d257	fix: move tool flags away from engine args	2024-12-06 16:07:23 +01:00
kldzj	3e86d16892	fix: openai tool calling	2024-12-06 13:08:48 +01:00
Marut PandyaandGitHub	d9f54ce76a	Update README.md	2024-11-29 16:30:45 -08:00
Marut PandyaandGitHub	149da95cd0	Merge pull request #133 from kldzj/tool-calling feat: add tool calling flags	2024-11-29 16:29:56 -08:00
Marut PandyaandGitHub	0a89394f1d	Update worker-config.json	2024-11-29 16:29:33 -08:00
Nikolai Kolodziej	8df7f41f1d	fix: set empty `tool_call_parser` to None	2024-11-24 06:55:43 +01:00
Nikolai Kolodziej	4d7b8c03c0	feat: tool calling flags	2024-11-24 06:51:41 +01:00