COMMITS
/ backend/python/vllm/backend.py May 1, 2026
April 28, 2026
R
feat(vllm): expose AsyncEngineArgs via generic engine_args YAML map (#9563)
Richard Palethorpe committed
April 13, 2026
E
feat(vllm): parity with llama.cpp backend (#9328)
Ettore Di Giacinto committed
March 29, 2026
E
feat: add distributed mode (#9124)
Ettore Di Giacinto committed
April 30, 2025
W
fix: vllm missing logprobs (#5279)
Wyatt Neal committed
April 19, 2025
E
chore: bump grpc limits to 50MB (#5212)
Ettore Di Giacinto committed
February 18, 2025
B
October 23, 2024
E
feat(vllm): expose 'load_format' (#3943)
Ettore Di Giacinto committed
October 20, 2024
E
fix(vllm): do not set videos if we don't have any (#3885)
Ettore Di Giacinto committed
October 17, 2024
E
fix(vllm): images and videos are base64 by default (#3867)
Ettore Di Giacinto committed
October 4, 2024
E
feat(vllm): add support for image-to-text and video-to-text (#3729)
Ettore Di Giacinto committed
September 2, 2024
E
feat(vllm): add support for embeddings (#3440)
Ettore Di Giacinto committed
May 11, 2024