Skip to content

[NeurIPS'24 Spotlight] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.

active 2024-07-03 → 2026-09-11 (UTC)

Complete coverage27,284 / 27,287 hourly files (100%) · 2 absent upstream2023-08-15 → 2026-09-24 (UTC)
Events
2K
Pushes
119
Pull requests
117
Issues
151
Stars
1.1K
Forks
63

Activity over time

Daily event counts in the loaded window

Line chart, 801 days from 2024-07-03 to 2026-09-11. Pushes: 119 total, peak 9 in a day. Pull requests: 117 total, peak 8 in a day. Issues: 151 total, peak 6 in a day. Comments: 308 total, peak 22 in a day. Stars: 1,071 total, peak 75 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

Recent activity

Latest issues, pull requests and releases

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,071 stars here means stars gained during the window, not the repo's star count.