Hannu Varjoranta
varjoranta
ยท
AI & ML interests
Weight and KV cache compression for production LLM serving. Building turboquant-plus-vllm.
Recent Activity
updated a model 11 days ago
varjosoft/Qwen3.6-35B-A3B-TQ-apex3 published a model 11 days ago
varjosoft/Qwen3.6-35B-A3B-TQ-apex3 updated a model 11 days ago
varjosoft/Qwen3.6-35B-A3B-TQ-apex2