qwen3.8-27b-rtx5090
Qwen3.8-27B on 2× RTX 5090 · 1.49M KV · code/prose t/s: c1 264/216, c16 2,649/2,240 · NVFP4 + vLLM + MTP
- 28
- Python
- 4 wk ago
Qwen3.8-27B on 2× RTX 5090 · 1.49M KV · code/prose t/s: c1 264/216, c16 2,649/2,240 · NVFP4 + vLLM + MTP
Upstream-maintained home for vendor L2 adapter plugins for LMCache
LMCache legacy InProcess engine as a separate Python package
Upstream-maintained home for vendor device plugins for LMCache