Kan Zhu
3 papers · 2024–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐ฃ
Hot Topic Early Bird
Top co-authors
Research topics
Keywords
model inference
(1)
kv cache
(1)
inference latency
(1)
beam search
(1)
self attention
(1)
gpu memory
(1)
intra-device parallelism
(1)
nano-batch scheduling
(1)
gpu throughput
(1)
resource overlapping
(1)
execution time optimization
(1)
cpu-gpu orchestration
(1)
criticality
(1)
query-aware
(1)
topk
(1)