owen/worker-vllm
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: upgrade vLLM to 0.19.1

Browse Source 
- Bump vllm[flashinfer] to 0.19.1 in Dockerfile
- Add OpenAIServingRender (new required dependency in 0.19.x serving layer)
- Pass openai_serving_render to all four serving class constructors
- Remove log_error_stack param (removed upstream in 0.19.x)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
velaraptor-runpod
2026-04-30 17:41:11 -05:00
co-authored by Claude Sonnet 4.6
parent a774cefe85
commit e6950bdebd
2 changed files with 25 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Dockerfile
+1 -1
View File
@@ -10,7 +10,7 @@ RUN ldconfig /usr/local/cuda-12.9/compat/
# Install vLLM with FlashInfer - use CUDA 12.9 PyTorch wheels
RUN uv pip install --system "packaging>=24.2" && \
uv pip install --system "vllm[flashinfer]==0.18.1" --extra-index-url https://download.pytorch.org/whl/cu129
uv pip install --system "vllm[flashinfer]==0.19.1" --extra-index-url https://download.pytorch.org/whl/cu129
# Install additional Python dependencies (after vLLM to avoid PyTorch version conflicts)
COPY builder/requirements.txt /requirements.txt
src/engine.py
+21 -3
View File
@@ -19,6 +19,7 @@ from vllm.entrypoints.openai.models.protocol import BaseModelPath, LoRAModulePat
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.openai.responses.protocol import ResponsesRequest, ResponsesResponse
from vllm.entrypoints.openai.responses.serving import OpenAIServingResponses
from vllm.entrypoints.serve.render.serving import OpenAIServingRender
from constants import DEFAULT_BATCH_SIZE, DEFAULT_BATCH_SIZE_GROWTH_FACTOR, DEFAULT_MAX_CONCURRENCY, DEFAULT_MIN_BATCH_SIZE
from engine_args import get_engine_args
@@ -252,10 +253,27 @@ class OpenAIvLLMEngine(vLLMEngine):
if self.tokenizer and hasattr(self.tokenizer, 'tokenizer'):
chat_template = self.tokenizer.tokenizer.chat_template
self.openai_serving_render = OpenAIServingRender(
model_config=self.llm.model_config,
renderer=self.llm.renderer,
io_processor=self.llm.io_processor,
model_registry=self.serving_models.registry,
request_logger=None,
chat_template=chat_template,
chat_template_content_format="auto",
trust_request_chat_template=os.getenv('TRUST_REQUEST_CHAT_TEMPLATE', 'false').lower() == 'true',
enable_auto_tools=os.getenv('ENABLE_AUTO_TOOL_CHOICE', 'false').lower() == 'true',
exclude_tools_when_tool_choice_none=os.getenv('EXCLUDE_TOOLS_WHEN_TOOL_CHOICE_NONE', 'false').lower() == 'true',
tool_parser=os.getenv('TOOL_CALL_PARSER', "") or None,
reasoning_parser=os.getenv('REASONING_PARSER', "") or None,
log_error_stack=os.getenv('LOG_ERROR_STACK', 'false').lower() == 'true',
)
self.chat_engine = OpenAIServingChat(
engine_client=self.llm,
models=self.serving_models,
response_role=self.response_role,
openai_serving_render=self.openai_serving_render,
request_logger=None,
chat_template=chat_template,
chat_template_content_format="auto",
@@ -268,20 +286,20 @@ class OpenAIvLLMEngine(vLLMEngine):
enable_prompt_tokens_details=os.getenv('ENABLE_PROMPT_TOKENS_DETAILS', 'false').lower() == 'true',
enable_force_include_usage=os.getenv('ENABLE_FORCE_INCLUDE_USAGE', 'false').lower() == 'true',
enable_log_outputs=os.getenv('ENABLE_LOG_OUTPUTS', 'false').lower() == 'true',
log_error_stack=os.getenv('LOG_ERROR_STACK', 'false').lower() == 'true',
)
self.completion_engine = OpenAIServingCompletion(
engine_client=self.llm,
models=self.serving_models,
openai_serving_render=self.openai_serving_render,
request_logger=None,
return_tokens_as_token_ids=os.getenv('RETURN_TOKENS_AS_TOKEN_IDS', 'false').lower() == 'true',
enable_prompt_tokens_details=os.getenv('ENABLE_PROMPT_TOKENS_DETAILS', 'false').lower() == 'true',
enable_force_include_usage=os.getenv('ENABLE_FORCE_INCLUDE_USAGE', 'false').lower() == 'true',
log_error_stack=os.getenv('LOG_ERROR_STACK', 'false').lower() == 'true',
)
self.responses_engine = OpenAIServingResponses(
engine_client=self.llm,
models=self.serving_models,
openai_serving_render=self.openai_serving_render,
request_logger=None,
chat_template=chat_template,
chat_template_content_format="auto",
@@ -293,12 +311,12 @@ class OpenAIvLLMEngine(vLLMEngine):
enable_prompt_tokens_details=os.getenv('ENABLE_PROMPT_TOKENS_DETAILS', 'false').lower() == 'true',
enable_force_include_usage=os.getenv('ENABLE_FORCE_INCLUDE_USAGE', 'false').lower() == 'true',
enable_log_outputs=os.getenv('ENABLE_LOG_OUTPUTS', 'false').lower() == 'true',
log_error_stack=os.getenv('LOG_ERROR_STACK', 'false').lower() == 'true',
)
self.messages_engine = AnthropicServingMessages(
engine_client=self.llm,
models=self.serving_models,
response_role=self.response_role,
openai_serving_render=self.openai_serving_render,
request_logger=None,
chat_template=chat_template,
chat_template_content_format="auto",