system paper reading notes
active 2023-09-03 → 2026-07-02 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 1034 days from 2023-09-03 to 2026-07-02. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 244 total, peak 74 in a day. Comments: 63 total, peak 6 in a day. Stars: 69 total, peak 3 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| pentium3 | 304 | 0 | 0 | 60 |
| kevin8023c | 1 | 0 | 0 | 1 |
| arc-arnob | 1 | 0 | 0 | 1 |
| TiankaiHang | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#440pentium32026-07-02 05:14Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs
- Issue#437pentium32026-06-07 05:02SystemX: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms
- Issue comment#436pentium32026-06-05 22:33AIMS: Cost-Efficient LLM-Based Agent Deployment in Hybrid Cloud-Edge Environments
- Issue#429pentium32026-06-05 21:55Adaptive Vision-Language Model Routing for Computer Use Agents
- Issue comment#426pentium32026-03-28 01:56SkillRouter: Retrieve-and-Rerank Skill Selection for LLM Agents at Scale
- Issue comment#426pentium32026-03-28 01:54SkillRouter: Retrieve-and-Rerank Skill Selection for LLM Agents at Scale
- Issue#422pentium32026-03-05 22:14Speculative Speculative Decoding
- Issue#420pentium32026-02-28 08:57AgentCgroup: Understanding and Controlling OS Resources of AI Agents
- Issue#416pentium32026-02-19 23:08ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference System
- Issue#415pentium32026-02-19 23:07Faster Cascades via Speculative Decoding
- Issue#415pentium32026-02-19 23:07Faster Cascades via Speculative Decoding
- Issue#413pentium32026-02-10 20:34Astraea: A state-aware scheduling engine for llm-powered agents
- Issue#413pentium32026-02-10 20:34Astraea: A state-aware scheduling engine for llm-powered agents
- Issue#410pentium32026-01-28 07:49mHC: Manifold-Constrained Hyper-Connections
- Issue comment#395pentium32026-01-28 07:18Speculative Actions: A Lossless Framework for Faster Agentic Systems
- Issue#409pentium32026-01-28 03:30Throughput-Optimal Scheduling Algorithms for LLM Inference and AI Agents
- Issue#409pentium32026-01-28 03:30Throughput-Optimal Scheduling Algorithms for LLM Inference and AI Agents
- Issue comment#389pentium32026-01-28 03:16NALAR: A Serving Framework for Agent Workflows
- Issue comment#389pentium32026-01-28 02:38NALAR: A Serving Framework for Agent Workflows
- Issue comment#392pentium32026-01-28 01:50Autellix: An Efficient Serving Engine for LLM Agents as General Programs
- Issue comment#392pentium32026-01-28 00:04Autellix: An Efficient Serving Engine for LLM Agents as General Programs
- Issue comment#392pentium32026-01-27 23:49Autellix: An Efficient Serving Engine for LLM Agents as General Programs
- Issue#407pentium32026-01-27 23:30Towards Agentic OS: An LLM Agent Framework for Linux Schedulers
- Issue#406pentium32026-01-27 08:21SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations
- Issue#405pentium32026-01-27 08:20Asteria: Semantic-Aware Cross-Region Caching for Agentic LLM Tool Access
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 69 stars here means stars gained during the window, not the repo's star count.