Keqin Qin
kisskissq
ยท
AI & ML interests
Efficient LLM inference, KV cache optimization, quantization, speculative decoding, model pruning
Recent Activity
liked a dataset about 11 hours ago
steven0226/speculative-decoding-bench-rtx4090 liked a dataset about 11 hours ago
Nathan-Maine/dgx-spark-kv-cache-benchmark liked a dataset about 11 hours ago
open-llm-leaderboard-old/details_saarvajanik__facebook-opt-6.7b-gqa-ub-16-best-for-KV-cacheOrganizations
None yet