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

Merge pull request #302 from runpod-workers/feat/0.22.1
Release / release (push) Waiting to run

Browse Source 
feat: upgrade vllm to 0.22.1
This commit is contained in:
chrisvela
2026-06-11 17:27:38 -05:00
committed by GitHub
parent d3a962c33b 5d1579e361
commit 5d9a48fc70
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.runpod/README.md
+1 -1
View File
@@ -6,7 +6,7 @@ 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)
Current vLLM version: [0.20.2](https://github.com/vllm-project/vllm/releases/tag/v0.20.2) Current vLLM version: [0.22.1](https://github.com/vllm-project/vllm/releases/tag/v0.22.1)
--- ---
Dockerfile
+1 -1
View File
@@ -21,7 +21,7 @@ ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:$LD_LIBRARY_PA
# Install vLLM with FlashInfer - use CUDA 130 PyTorch wheels # Install vLLM with FlashInfer - use CUDA 130 PyTorch wheels
RUN uv pip install --system "packaging>=24.2" && \ RUN uv pip install --system "packaging>=24.2" && \
uv pip install --system "vllm[flashinfer]==0.21.0" && \ uv pip install --system "vllm[flashinfer]==0.22.1" && \
uv pip install --system git+https://github.com/deepseek-ai/DeepGEMM.git@714dd1a4a980f7937a74343d19a8eba4fe321480 --no-build-isolation uv pip install --system git+https://github.com/deepseek-ai/DeepGEMM.git@714dd1a4a980f7937a74343d19a8eba4fe321480 --no-build-isolation
# Install additional Python dependencies (after vLLM to avoid PyTorch version conflicts) # Install additional Python dependencies (after vLLM to avoid PyTorch version conflicts)
README.md
+1 -1
View File
@@ -8,7 +8,7 @@ Deploy OpenAI-Compatible Blazing-Fast LLM Endpoints powered by the [vLLM](https:
![vLLM worker banner](https://image.runpod.ai/preview/vllm/vllm-banner.png) ![vLLM worker banner](https://image.runpod.ai/preview/vllm/vllm-banner.png)
Current vLLM version: [0.20.2](https://github.com/vllm-project/vllm/releases/tag/v0.20.2) Current vLLM version: [0.22.1](https://github.com/vllm-project/vllm/releases/tag/v0.22.1)
> Check out our Load Balancer implementation here: [vLLM Load Balancer](https://github.com/runpod-workers/vllm-loadbalancer-ep) > Check out our Load Balancer implementation here: [vLLM Load Balancer](https://github.com/runpod-workers/vllm-loadbalancer-ep)