Topic

Awq

1 items across the graph — tagged with Awq.

From the graph · 1

repo
aivrar/vllm-windows-build

Native Windows builds of vLLM 0.25.1 with CUDA 12.8, Python 3.13, Multi-TurboQuant, and experimental CPU/NVMe KV-cache offload.

→

Related topics

cuda 1llm-inference 1llm 1gpu 1flash-attention 1msvc 1kv-cache 1llm-serving 1kv-cache-compression 1awq 1
Search Awq →All topics →