Author

Bilibili Tech

Provides introductions and tutorials on Bilibili-related technologies.

396

Articles

Likes

1.2k

Views

Comments

Latest from Bilibili Tech

100 recent articles max

Bilibili Tech

Dec 31, 2024 · Cloud Computing

Design and Implementation of Bilibili AI Compute Network: Topology, Hardware Selection, Load Balancing, and Monitoring

Bilibili designed and deployed an AI compute network for large language model training, choosing a Fat-Tree topology, selecting high‑speed switches, optical modules, and fibers, implementing fixed‑path load balancing, and building a sub‑second telemetry monitoring platform, with plans to scale to ten‑thousand GPUs.

AI compute networkFat-Tree topologyhardware selection

0 likes · 17 min read

Design and Implementation of Bilibili AI Compute Network: Topology, Hardware Selection, Load Balancing, and Monitoring

Bilibili Tech

Dec 27, 2024 · Big Data

Consistency Architecture for Bilibili Recommendation Model Data Flow

The article outlines Bilibili’s revamped recommendation data‑flow architecture that eliminates timing and calculation inconsistencies by snapshotting online features, unifying feature computation in a single C++ library accessed via JNI, and orchestrating label‑join and sample extraction through near‑line Kafka/Flink pipelines, with further performance gains and Iceberg‑based future extensions.

Data ConsistencyFlinkIceberg

0 likes · 12 min read

Consistency Architecture for Bilibili Recommendation Model Data Flow

Bilibili Tech

Dec 24, 2024 · Artificial Intelligence

AniSora: An Integrated System for Anime Video Generation with Data Flywheel, Controllable Diffusion Models, and Evaluation Benchmark

AniSora combines a 10‑million‑pair anime text‑video dataset, a controllable diffusion‑transformer with temporal‑mask conditioning for text‑to‑video, interpolation and region‑guided animation, and a 948‑video benchmark, delivering industry‑leading character and motion consistency and already powering low‑cost dynamic‑comic production for multiple IPs.

AI_AnimationDataset BenchmarkDiffusion Models

0 likes · 21 min read

AniSora: An Integrated System for Anime Video Generation with Data Flywheel, Controllable Diffusion Models, and Evaluation Benchmark

Bilibili Tech

Dec 20, 2024 · Operations

Evolution of Bilibili's Server Provisioning System: From Traditional PXE to BiliOS and iPXE

To cope with rapid growth, Bilibili replaced its inflexible PXE workflow with a hybrid system using in‑memory BiliOS and iPXE, adding out‑of‑band management, declarative configuration, and multi‑scenario support, which together dramatically boosted provisioning automation, reliability, and efficiency across its data‑center and edge servers.

BiliOSInfrastructurePXE

0 likes · 17 min read

Evolution of Bilibili's Server Provisioning System: From Traditional PXE to BiliOS and iPXE

Bilibili Tech

Dec 17, 2024 · Big Data

Apache Gravitino: Metadata Management Practices and Production Experience at Bilibili

Bilibili adopted Apache Gravitino as a unified metadata platform that decouples consumers, consolidates schemas and Fileset‑based unstructured data across heterogeneous sources, cuts metadata and storage costs, resolves inconsistencies, boosts Hive Metastore performance, and enables features such as Iceberg branching and future AI‑centric governance.

Apache GravitinoBig DataFileset

0 likes · 20 min read

Apache Gravitino: Metadata Management Practices and Production Experience at Bilibili

Bilibili Tech

Dec 13, 2024 · Databases

Design and Implementation of a Multi-Level Storage Architecture for Bilibili Comment Service

The paper proposes a multi‑level storage architecture for Bilibili’s comment service that replaces TiDB with a custom KV store (Taishan) and Redis caching, introduces unstructured indexes, CAS‑based consistency, real‑time and offline reconciliation, and a hedged degradation strategy to boost reliability, read throughput, and scalability during traffic spikes.

Data ConsistencyNoSQLRedis

0 likes · 13 min read

Design and Implementation of a Multi-Level Storage Architecture for Bilibili Comment Service

Bilibili Tech

Dec 10, 2024 · Big Data

Fault Self‑Healing System for Bilibili's Large‑Scale Big Data Cluster (BMR)

Bilibili's fault‑self‑healing platform for its massive BMR big‑data cluster—over 10,000 machines and 1 EB storage—adds near‑real‑time fault discovery, intelligent diagnosis, and automated workflow handling, dramatically cutting resolution time, improving stability across services, and scaling to dozens of daily automated repairs.

BMRCluster Managementfault self-healing

0 likes · 16 min read

Fault Self‑Healing System for Bilibili's Large‑Scale Big Data Cluster (BMR)

Bilibili Tech

Dec 6, 2024 · Artificial Intelligence

Ensemble-based Offline-to-Online Reinforcement Learning (ENOTO): Methodology, Experiments, and Analysis

ENOTO introduces ensemble Q‑networks into the offline‑to‑online reinforcement‑learning pipeline, using minimum‑Q and uncertainty‑driven exploration to stabilize fine‑tuning, boost learning efficiency, and achieve 10‑25 % higher cumulative returns with minimal online interaction across MuJoCo and AntMaze benchmarks.

AntMazeENOTOEnsemble Q-Networks

0 likes · 16 min read

Ensemble-based Offline-to-Online Reinforcement Learning (ENOTO): Methodology, Experiments, and Analysis

Bilibili Tech

Dec 3, 2024 · Frontend Development

Design and Implementation of a WASM Demuxer for WebCodecs Video Frame Extraction

The project extracts FFmpeg’s demuxing logic into a lightweight WebAssembly module that feeds container‑agnostic video packets to WebCodecs, enabling fast, low‑cost frame extraction across many formats and cutting cover‑generation latency by ~40% while reducing container‑related failures by ~72%.

Video DemuxingWebAssemblyWebCodecs

0 likes · 11 min read

Design and Implementation of a WASM Demuxer for WebCodecs Video Frame Extraction

Bilibili Tech

Nov 29, 2024 · R&D Management

Design and Implementation of Bilibili's Self‑Developed Video Editing Engine

Bilibili replaced a restrictive third‑party video editor with a self‑developed engine, redesigning architecture for extensibility, manageability and controllable rollout, refactoring hundreds of API calls, enabling draft migration, adding observability, and achieving lower crash rates, faster timelines and stable conversion gains while continuing AI‑assisted feature expansion.

BilibiliEngine ArchitecturePerformance Metrics

0 likes · 13 min read

Design and Implementation of Bilibili's Self‑Developed Video Editing Engine