Skip to content

feat: GPU support for building DISKANN based indexes.

active 2023-08-152026-08-25 (UTC)

Complete coverage26,741 / 26,741 hourly files (100%) · 2 absent upstream2023-08-152026-09-02 (UTC)
Events
17.9K
Pushes
916
Pull requests
7.3K
Issues
706
Stars
259
Forks
115

Activity over time

Daily event counts in the loaded window

Line chart, 1107 days from 2023-08-15 to 2026-08-25. Pushes: 916 total, peak 11 in a day. Pull requests: 7,253 total, peak 929 in a day. Issues: 706 total, peak 31 in a day. Comments: 6,723 total, peak 59 in a day. Stars: 259 total, peak 6 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

ContributorContributionsPushesPRsComments
mergify[bot]5.9K05.2K744
sre-ci-robot3.3K7449281.6K
alexanderguzhva1.4K090951
foxspy92916240401
liliu-z8804166463
cydrain8255191479
zhengbuqian552362341
github-actions[bot]413027210
Presburger3834362158
cqy123456378078175
chasingegg363585162
codecov[bot]27000270
alwayslove201321584692
PwzXxm184019113
sparknack14222677
adarshs1310870267
wphicks760744
hhy3740634
lyang24650542
samhuang-z5713023

Recent activity

Latest issues, pull requests and releases

  • Pull request#1786marcelo-cjl2026-08-21 13:38
  • Issue comment#1689sre-ci-robot2026-06-29 07:41
    fix: dispatch SVE from baseline ARM hook
  • Issue comment#1650github-actions[bot]2026-06-27 02:24
    ARM/x86 HNSW_SQ SQ4U build regression after ScalarQuantizer migration: `symmetric_dis` lost SIMD fastpath
  • Pull request#1683mergify[bot]2026-06-17 10:36
  • Issue comment#1628github-actions[bot]2026-06-16 02:25
    Separate “cheap upper-bound scoring for candidate generation” from “exact BM25 scoring for final ranking”.
  • Issue comment#1671sre-ci-robot2026-06-15 03:11
    enhance: sparse: optimize dim map mmap loading
  • Pull request#1673mergify[bot]2026-06-13 02:18
  • Pull request#1670sre-ci-robot2026-06-09 08:54
  • Pull request#1669mergify[bot]2026-06-09 04:27
  • Issue#1548github-actions[bot]2026-06-08 02:25
    [Feature Request] IVFRaBitQ: support multibit RaBitQ+ codes (nb_bits > 1) in both regular and FastScan paths
  • Issue comment#1611github-actions[bot]2026-06-04 02:23
    AISAQ Improvements
  • Issue comment#1664sparknack2026-06-04 02:04
    enhance: sparse: add skip_window_calc pruning for SINDI search
  • Issue comment#1659sre-ci-robot2026-06-02 05:34
    bump milvus-common and cardinalv1 version
  • Pull request#1659sre-ci-robot2026-06-02 05:34
  • Pull request#1661sre-ci-robot2026-06-01 06:44
  • Issue comment#1659mergify[bot]2026-05-30 05:54
    bump milvus-common version
  • Issue#1501github-actions[bot]2026-05-30 02:24
    Upgrade Faiss to 1.14.1+ and merge the fork with the baseline as much as possible
  • Issue#1598github-actions[bot]2026-05-30 02:24
    bug: ARM e2e pods OOM at reduced 12Gi memory requests
  • Issue comment#1608github-actions[bot]2026-05-30 02:24
    Migrate to a newer folly version
  • Issue comment#1607github-actions[bot]2026-05-29 02:25
    enable RVV after #1594
  • Issue#1604github-actions[bot]2026-05-28 02:24
    e2e-SSE zombie pods on CI
  • Issue comment#1604github-actions[bot]2026-05-28 02:24
    e2e-SSE zombie pods on CI
  • Pull request#1653sre-ci-robot2026-05-27 19:19
  • Pull request#1649mergify[bot]2026-05-27 12:10
  • Issue comment#1649sre-ci-robot2026-05-27 12:10
    fix: filter system fields from vanilla FAISS params

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 259 stars here means stars gained during the window, not the repo's star count.