deepseek-ai/DeepSeek-V4.1-Flash-1017 Image-Text-to-Text • 763B • Updated 13 days ago • 515k • • 5.84k
Qwen3.8-27B latent attention retrofits Collection Training-free MLA / GLA retrofits of Qwen3.8-27B with a 2x smaller KV cache. Weights preview; vLLM plugin, quants and code coming early October 2026. • 8 items • Updated Oct 15 • 6
Qwen3.8-27B latent attention retrofits Collection Training-free MLA / GLA retrofits of Qwen3.8-27B with a 2x smaller KV cache. Weights preview; vLLM plugin, quants and code coming early October 2026. • 8 items • Updated Oct 15 • 6