Aquifer is the first system to serve MicroVM snapshots from a hierarchical CXL+RDMA memory pool using hotness-based formatting, ownership coherence, and copy-based serving, delivering 2.2x speedup over Firecracker.
In Proceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles (SOSP '24), 2024
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
fields
cs.DC 6verdicts
UNVERDICTED 6representative citing papers
Scepsy schedules arbitrary multi-LLM agentic workflows on GPU clusters by constructing Aggregate LLM Pipelines from stable per-LLM execution time shares, then searching fractional GPU allocations, tensor parallelism, and replica counts to achieve up to 2.4x higher throughput and 27x lower latency.
Amoeba adaptively adjusts tensor parallelism at runtime for LLM inference services to handle mixed short and long context requests, delivering 1.75x-6.57x throughput gains over prior solutions in real-world trace evaluations.
eLLM unifies LLM memory management with virtual tensors and elastic ballooning to CPU memory, reporting 2.32x higher decoding throughput and 3x larger batch sizes for 128K inputs.
KernelFlume presents a disaggregated decode architecture that separates core attention from projection/FFN paths to enable elastic scaling of attention nodes, reporting up to 61% lower cost per million tokens versus full-instance scaling on H100 hardware for Llama-3.1-8B under dynamic long-context w
Ambulance uses protocol-rigged races among replicas to achieve high throughput and low latency comparable to timeout-based BFT while matching the robustness of cooperative approaches.
citing papers explorer
-
Aquifer: Hierarchical Memory Pooling with CXL and RDMA for MicroVM Snapshots
Aquifer is the first system to serve MicroVM snapshots from a hierarchical CXL+RDMA memory pool using hotness-based formatting, ownership coherence, and copy-based serving, delivering 2.2x speedup over Firecracker.
-
Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines
Scepsy schedules arbitrary multi-LLM agentic workflows on GPU clusters by constructing Aggregate LLM Pipelines from stable per-LLM execution time shares, then searching fractional GPU allocations, tensor parallelism, and replica counts to achieve up to 2.4x higher throughput and 27x lower latency.
-
Amoeba: Runtime Tensor Parallel Transformation for LLM Inference Services
Amoeba adaptively adjusts tensor parallelism at runtime for LLM inference services to handle mixed short and long context requests, delivering 1.75x-6.57x throughput gains over prior solutions in real-world trace evaluations.
-
eLLM: Elastic Memory Management Framework for Efficient LLM Serving
eLLM unifies LLM memory management with virtual tensors and elastic ballooning to CPU memory, reporting 2.32x higher decoding throughput and 3x larger batch sizes for 128K inputs.
-
KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding
KernelFlume presents a disaggregated decode architecture that separates core attention from projection/FFN paths to enable elastic scaling of attention nodes, reporting up to 61% lower cost per million tokens versus full-instance scaling on H100 hardware for Llama-3.1-8B under dynamic long-context w
-
Ambulance: saving BFT through racing
Ambulance uses protocol-rigged races among replicas to achieve high throughput and low latency comparable to timeout-based BFT while matching the robustness of cooperative approaches.