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

update vllm

Browse Source 
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
This commit is contained in:
pandyamarut
2025-02-24 15:01:45 -08:00
parent 6dcf39e159
commit 56dc4ad075
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Dockerfile
+1 -1
View File
@@ -12,7 +12,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
python3 -m pip install --upgrade -r /requirements.txt 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 (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==0.7.2 && \ RUN python3 -m pip install vllm==0.7.3 && \
python3 -m pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3 python3 -m pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3
# Setup for Option 2: Building the Image with the Model included # Setup for Option 2: Building the Image with the Model included
src/utils.py
+1 -1
View File
@@ -44,7 +44,7 @@ class JobInput:
self.max_batch_size = job.get("max_batch_size") self.max_batch_size = job.get("max_batch_size")
self.apply_chat_template = job.get("apply_chat_template", False) self.apply_chat_template = job.get("apply_chat_template", False)
self.use_openai_format = job.get("use_openai_format", False) self.use_openai_format = job.get("use_openai_format", False)
self.sampling_params = SamplingParams(**job.get("sampling_params", {})) self.sampling_params = SamplingParams(max_tokens=100, **job.get("sampling_params", {}))
self.request_id = random_uuid() self.request_id = random_uuid()
batch_size_growth_factor = job.get("batch_size_growth_factor") batch_size_growth_factor = job.get("batch_size_growth_factor")
self.batch_size_growth_factor = float(batch_size_growth_factor) if batch_size_growth_factor else None self.batch_size_growth_factor = float(batch_size_growth_factor) if batch_size_growth_factor else None