TurboServe introduces the first serving system for streaming video generation workloads, using migration-aware placement and load-driven autoscaling to cut worst-case latency by 37.5% and GPU cost by 37.2%.
Hexgen-2: Disaggregated generative inference of llms in heterogeneous environment
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
fields
cs.DC 6roles
background 3polarities
background 3representative citing papers
HexAGenT reduces the SLO scale required for timely agentic LLM workflow completion by an average of 20.1% at 95% attainment and 33.0% at 99% attainment on heterogeneous A100/H100/H200 clusters.
Autopoiesis uses LLM-driven program synthesis to evolve serving policies online during deployment, delivering up to 53% and average 34% gains over prior LLM serving systems under runtime dynamics.
HexiSeq optimizes sequence and head partitioning across mixed GPUs to improve long-context LLM training throughput by up to 1.72x in simulations.
R-DSGD and R-DSGD-M under (δ,c)-robust aggregation have tight Byzantine error floors under (B,ζ)-bounded dissimilarity; local momentum eliminates the stochastic-noise term but not the heterogeneity term.
HexiScale enables LLM training on heterogeneous GPUs via asymmetric parallelism and graph partitioning, matching homogeneous performance at equal FLOPS and delivering 1.5-2.4x higher throughput than prior heterogeneous systems.
citing papers explorer
-
TurboServe: Serving Streaming Video Generation Efficiently and Economically
TurboServe introduces the first serving system for streaming video generation workloads, using migration-aware placement and load-driven autoscaling to cut worst-case latency by 37.5% and GPU cost by 37.2%.
-
HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling
HexAGenT reduces the SLO scale required for timely agentic LLM workflow completion by an average of 20.1% at 95% attainment and 33.0% at 99% attainment on heterogeneous A100/H100/H200 clusters.
-
Autopoiesis: A Self-Evolving System Paradigm for LLM Serving Under Runtime Dynamics
Autopoiesis uses LLM-driven program synthesis to evolve serving policies online during deployment, delivering up to 53% and average 34% gains over prior LLM serving systems under runtime dynamics.
-
HexiSeq: Accommodating Long Context Training of LLMs over Heterogeneous Hardware
HexiSeq optimizes sequence and head partitioning across mixed GPUs to improve long-context LLM training throughput by up to 1.72x in simulations.
-
Tessera: Unlocking Heterogeneous GPUs through Kernel-Granularity Disaggregation
R-DSGD and R-DSGD-M under (δ,c)-robust aggregation have tight Byzantine error floors under (B,ζ)-bounded dissimilarity; local momentum eliminates the stochastic-noise term but not the heterogeneity term.
-
HexiScale: Facilitating Large Language Model Training over Heterogeneous Hardware
HexiScale enables LLM training on heterogeneous GPUs via asymmetric parallelism and graph partitioning, matching homogeneous performance at equal FLOPS and delivering 1.5-2.4x higher throughput than prior heterogeneous systems.