Fan Yang
where else to find them
linkedin:fyang26
what they talk about
all 8 in the filters
where they keep going back
no series more than once — all 8 in the filters
on a stage with
all 92 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Cost-efficient Archive Cloud Storage with Tape: Design and Deployment | FAST '26 | 2026-02-24 |
TapeOBS claims tape reduces TCO 4.95× and CO2e by 97% and runs in production storing hundreds of petabytes since 2024. It uses a 4% HDD staging pool to make a… | ||
| Outline and Detail: A Semantic-Driven Framework for Layered 2D Character Generation | UIST 2025 | 2025-09-28 |
A pipeline called Spiritus produces layered, rigged 2D characters from mixed text and sketch inputs in minutes by semantic-matching prompts to an open mask… | ||
| WaferLLM: Large Language Model Inference at Wafer Scale | OSDI '25 | 2025-07-07 |
WaferLLM adapts LLM inference to wafer-scale chips using a PLMR model that guides placement and communication, implements MeshGEMM and MeshGEMV operators, and… | ||
| PipeThreader: Software-Defined Pipelining for Efficient DNN Execution | OSDI '25 | 2025-07-07 |
A compiler shifts pipeline scheduling from hardware to software, exposing tile-level tasks and heterogeneous units to generate efficient DNN pipelines. It… | ||
| Ladder: Enabling Efficient Low-Precision Deep Learning Computing through... | 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI '24) | 2024-07-10 |
Ladder is a compiler that represents evolving low‑bit formats as a first‑class tType and exposes four concrete tensor transforms (slice/map/convert/pad) to… | ||
| nnScaler: Constraint-Guided Parallelization Plan Generation for Deep Learning Training | 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI '24) | 2024-07-10 |
A plan-generation framework implements three primitives op-trans, op-assign, op-order plus constraint filters so experts compose custom parallelization spaces… | ||
| Parrot: Efficient Serving of LLM-based Applications with Semantic Variable | 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI '24) | 2024-07-10 |
Parrot is an LLM-serving system that exposes Semantic Variable annotations so the service sees the dataflow across multiple prompt requests and can do… | ||
| VBASE: Unifying Online Vector Similarity Search and Relational Queries via Relaxed... | OSDI 2023 | 2023-07-10 |
VBase identifies a property called relaxed monotonicity that lets approximate nearest-neighbor indices serve as termination checks for SQL-style queries… | ||
| Cocktailer: Analyzing and Optimizing Dynamic Control Flow in Deep Learning | OSDI 2023 | 2023-07-10 |
OSDI '23 - Cocktailer: Analyzing and Optimizing Dynamic Control Flow in Deep Learning
Chen Zhang, Tsinghua University, Lingxiao Ma, Microsoft Research, Jilong… | ||
| Welder: Scheduling Deep Learning Memory Access via Tile-graph | OSDI 2023 | 2023-07-10 |
Welder is a deep-learning compiler that builds a tile-graph abstraction to connect operators at register/shared-memory levels and schedule tiling across… | ||
| Optimizing Dynamic Neural Networks with Brainstorm | OSDI 2023 | 2023-07-10 |
Brainstorm introduces Cell as the sub-tensor routing unit and Router as a programmable dispatch operator, collects fine-grained runtime profiles, and applies… | ||
| On Modular Learning of Distributed Systems for Predicting End-to-End Latency | NSDI 2023 | 2023-04-17 |
Fluxion builds a modular performance model by packaging per-service ML models into learning assignments and wiring them into an inference graph so changes only… | ||
| PilotFish: Harvesting Free Cycles of Cloud Gaming with Deep Learning Training | USENIX ATC '22 | 2022-07-11 |
PilotFish co-locates deep learning training with cloud gaming, hooks DirectX/OpenGL to capture idle GPU periods in sub-millisecond granularity, and schedules… | ||
| Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads | USENIX ATC '19 | 2019-07-10 |
Analysis uses a 75‑day trace from Microsoft Philly (shared by 14 production groups) combining scheduler logs, hardware counters and AI‑engine logs to profile… | ||
| nothing matches | ||