Search papers, labs, and topics across Lattice.
5
0
8
Reorganizing expert groups in MoE models can slash accuracy degradation by over 71% while boosting throughput by more than twofold.
Cold start latencies can be slashed by up to 99.3% with CoCoScale's innovative layer-wise scaling approach.
RolloutPipe slashes rollout-to-training time by up to 42% while keeping on-policy correctness intact, revolutionizing resource efficiency in LLM training.
SwiftCache slashes latency by 69% and boosts context length nearly fourfold by enabling cross-model KV cache sharing on GPUs.
LLM scaling bottlenecks demand a shift towards cloud-native architectures and distributed systems, unlocking potential gains from serverless inference and quantum computing.
