Xin Jin
where else to find them
linkedin:jinxin
what they talk about
all 14 in the filters
where they keep going back
no series more than once — all 11 in the filters
on a stage with
all 109 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| FastServe: Iteration-Level Preemptive Scheduling for Large Language Model Inference | NSDI '26 | 2026-05-04 |
FastServe implements iteration-level preemption for autoregressive LLMs, letting the system preempt after each token instead of running to completion. It… | ||
| HydraServe: Minimizing Cold Start Latency for Serverless LLM Serving in Public Clouds | NSDI '26 | 2026-05-04 |
HydraServe implements pipeline parallelism, stage overlapping, and pipeline consolidation to cut serverless LLM cold starts that can reach 45 seconds (model… | ||
| Iceberg: Automated Verification of DNS Authoritative Engines via Just-in-Time... | NSDI '26 | 2026-05-04 |
Iceberg implements just-in-time summarization over LLVM IR with Z3 to verify DNS authoritative engines automatically, using state splitting, symbolic regions… | ||
| KUBEDIRECT: Unleashing the Full Power of the Cluster Manager for Serverless Computing | NSDI '26 | 2026-05-04 |
KUBEDIRECT bypasses the API server and uses direct P2P message passing along a sequential controller chain, implementing pairwise agreements as a hierarchical… | ||
| DistRS: Disaggregated Reward Service for RLVR with Batch-Level Constraint | NSDI '26 | 2026-05-04 |
DistRS is a disaggregated reward service that separates reward computation from training, implements a microservice pipeline with per-stage worker pools, and… | ||
| A Composable Emulation Framework for Whitebox Switches | NSDI '26 | 2026-05-04 |
MirSwitch composes a production SONiC control plane with a modified VPP data plane and virtualized peripheral modules using an adapter-centric design: EVPP… | ||
| ServeGen: Workload Characterization and Generation of Large Language... | NSDI '26 | 2026-05-04 |
Characterization uses production traces spanning 3.5 billion requests over 4 months across 10 models and finds that traffic is dominated by a few customers —… | ||
| MeshTest: End-to-End Testing for Service Mesh Traffic Management | NSDI '25 | 2025-04-28 |
MeshTest automatically generates end-to-end service mesh configs using a novel Service Flow Exploration to enumerate resource interactions, then translates… | ||
| Optimizing RLHF Training for Large Language Models with Stage Fusion | NSDI '25 | 2025-04-28 |
RLHFuse claims up to 3.7× end-to-end RLHF training throughput by splitting tasks into sample-level subtasks and microbatch subtasks. It overlaps generation and… | ||
| DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language... | 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI '24) | 2024-07-10 |
System disaggregates prefill and decoding onto separate GPUs, assigns independent parallelism and resource plans for each phase, and places instances to cut… | ||
| Burstable Cloud Block Storage with Data Processing Units | 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI '24) | 2024-07-10 |
An end-to-end system called BurstCBS runs on DPUs to balance per-core load with added FPGA queues, uses a two-tier memory pool to prefill buffers without… | ||
| dLoRA: Dynamically Orchestrating Requests and Adapters for LoRA LLM Serving | 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI '24) | 2024-07-10 |
dLoRA is a LoRA-serving system that dynamically merges and unmerges adapters and migrates both requests and adapters to reduce latency and boost GPU… | ||
| Fast Vector Query Processing for Large Datasets Beyond GPU Memory with Reordered... | 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI '24) | 2024-04-16 |
RUMMY is a GPU-backed vector query engine that pipelines host-to-GPU transfers and computation to handle billion-scale datasets beyond GPU RAM. It implements… | ||
| Jolteon: Unleashing the Promise of Serverless for Serverless Workflows | 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI '24) | 2024-04-16 |
An orchestrator called Jolteon implements a stochastic performance model combining analytical whitebox formulas and blackbox variability, formulates a… | ||
| MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs | 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI '24) | 2024-04-16 |
MegaScale is a production system that trains LLMs on more than 10,000 GPUs and achieves concrete gains: 55.2% Model FLOPs Utilization when training a 175B… | ||
| AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving | OSDI 2023 | 2023-07-10 |
AlpaServe uses model parallelism not just to fit big models but to statistically multiplex GPUs across many models, trading partition overhead for burst… | ||
| Transparent GPU Sharing in Container Clouds for Deep Learning Workloads | NSDI 2023 | 2023-04-17 |
Claims a kernel‑intercept OS layer called TGS that enables transparent GPU sharing under Docker/Kubernetes with ~3000 LOC, adaptive rate control and… | ||
| Fast, Approximate Vector Queries on Very Large Unstructured Datasets | NSDI 2023 | 2023-04-17 |
Auncel provides bounded query error and bounded latency for billion-item vector search by building a per-query error-latency profile that predicts how many… | ||
| NetVRM: Virtual Register Memory for Programmable Networks | 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI '22) | 2022-04-04 |
NetVRM provides a virtual register memory abstraction plus a P4VRM compiler that merges multiple P4 programs so on-chip register regions are remapped at… | ||
| Twenty Years After: Hierarchical Core-Stateless Fair Queueing | NSDI ’21 | 2021-04-12 |
Implements Core-Stateless Fair Queueing on programmable switches and generalizes it to Hierarchical CSFQ that approximates hierarchical fair queuing while… | ||
| Ship Compute or Ship Data? Why Not Both? | NSDI ’21 | 2021-04-12 |
Kayak is a prototype that adaptively splits requests between a KV (ship data) path and an RPC (ship compute) path by tuning rate limit and request fraction… | ||
| Multitenancy for Fast and Programmable Networks in the Cloud | HotCloud '20 | 2020-07-13 |
Claims that a hybrid compile-time linker plus a runtime stateful-memory allocator lets multiple tenant P4 programs share a Barefoot Tofino ASIC with low… | ||
| DistCache: Provable Load Balancing for Large-Scale Storage Systems with Distributed Caching | USENIX ATC '19 | 2019-07-10 |
DistCache splits a single hot-cache into many small nodes, allocating hot items with two independent hash functions and routing queries with the… | ||
| NetChain: Scale-Free Sub-RTT Coordination | NSDI '18 | 2018-04-09 |
NetChain moves the replicated coordination KV store into programmable switches (PISA) to cut client-visible latency to about 9.7 microseconds and to push… | ||
| nothing matches | ||