Youssef Amrani
youssefam
ยท
AI & ML interests
Efficient LLM inference, KV cache optimization, quantization, speculative decoding, model pruning
Recent Activity
liked a dataset 3 days ago
ergt2025/kvcache_offload upvoted a paper 3 days ago
QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World ModelsOrganizations
None yet