vllm-project/tpu-inference
TPU inference for vLLM, with unified JAX and PyTorch support.
docs.vllm.ai/projects/tpu ↗github.com/vllm-project/tpu-inference ↗
Outside contributors get merged here, though some wait a while for a reply. Replies are slow here: typically 7.7 days, beyond your 7-day budget.
18 of 62outside PRs merged (29%)
checked
Where newcomer work lands
The evidence