Call https://github.com/chenwenxiaolive if you find any BUG!
410
Serve IQuest-Q1 with vLLM: reasoning, tool calling, and MTP speculative decoding. CUDA 13.0.
Content type
Image
Digest
sha256:e316872c5…
Size
9.1 GB
Last updated
17 days ago
docker pull iquestlabworkspace/vllm-iquest-q1:cu130