Searching protocol for "Ascend"
Adapt vLLM Ascend to the latest main branch.
OpenAI-compatible LLM serving on Ascend NPUs.
Guide AscendC transformer op development.
Adapt and test models for vLLM Ascend quickly.
Adapt models for vLLM on Ascend NPU.
Compress and deploy Ascend models.
Ascend Docker: efficient NPU container setups.
Draft release notes for vLLM Ascend
Detect Ascend profiler regressions quickly
Analyze PyTorch models for Ascend NPU readiness.
Diagnose and optimize Ascend NPU computation.
Sync vLLM main branch to vLLM Ascend.