Running
1
SJ-KVaRN
📄
Compress LLM KV‑cache to fit longer contexts on limited GPU memory
Jake PRO
jakeatx
AI & ML interests
distillation, MoE tuning + optimizing, offloading
Recent Activity
updated a collection 2 days ago
Qwen3.8 Flash-Next published a model 2 days ago
jakeatx/qwen3.8-flash-next-Swift1.5-ATX-AI4 updated a model 2 days ago
jakeatx/qwen3.8-flash-next-Swift1.5-ATX-AI4Organizations
None yet