Skip to content

A PyTorch library and evaluation platform for end-to-end compression research

active 2025-01-032026-07-14 (UTC)

Partial coverage12,397 / 14,106 hourly files (88%) · 2 absent upstream · 1,703 failed, retryable2024-12-312026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
213
Pushes
17
Pull requests
2
Issues
12
Stars
144
Forks
12

Activity over time

Daily event counts in the loaded window

Line chart, 558 days from 2025-01-03 to 2026-07-14. Pushes: 17 total, peak 8 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 12 total, peak 1 in a day. Comments: 18 total, peak 2 in a day. Stars: 144 total, peak 5 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

  • Issue comment#349fracape2026-03-11 00:24
    fix: update torch.amp.autocast to use modern API
  • Pull request#350studyingeugene2025-12-16 13:06
  • Issue#348teaandscones2025-11-04 13:33
    Encoding distribution and "true" distribution modeling
  • Issue comment#345studyingeugene2025-10-26 04:36
    Clarification on the design philosophy of LowerBound
  • Issue comment#345studyingeugene2025-10-25 05:11
    Clarification on the design philosophy of LowerBound
  • Issue comment#345studyingeugene2025-10-25 04:46
    Clarification on the design philosophy of LowerBound
  • Issue comment#345YodaEmbedding2025-10-24 23:34
    Clarification on the design philosophy of LowerBound
  • Issue#345studyingeugene2025-10-24 19:12
    Clarification on the design philosophy of LowerBound
  • Pull request#343studyingeugene2025-10-17 17:19
  • Issue#342zb121382025-08-23 15:41
    Change the installed torch version after installing Compressor AI
  • Issue comment#308uzumaki6712025-07-31 13:35
    EntropyBottleneck with adjustable bin width
  • Issue comment#189paomian0012025-07-21 13:42
    get different kodak dataset testing result using VTM
  • Issue comment#339DoctorHaibara2025-05-17 02:35
    [Bug] Incompatible pointops version – furthestsampling() missing 'new_offset'
  • Issue#339DoctorHaibara2025-05-17 02:35
    [Bug] Incompatible pointops version – furthestsampling() missing 'new_offset'
  • Issue comment#337YodaEmbedding2025-05-10 08:00
    How to .update() a GaussianConditional entropy model and properly call .compress() and .decompress()?
  • Issue comment#338YodaEmbedding2025-05-10 07:45
    win11 install failed
  • Issue#338theSlowBird2025-05-09 22:47
    win11 install failed
  • Issue comment#337johnli252025-05-08 23:32
    How to .update() a GaussianConditional entropy model and properly call .compress() and .decompress()?
  • Issue#337johnli252025-05-08 23:32
    How to .update() a GaussianConditional entropy model and properly call .compress() and .decompress()?
  • Issue#336paomian0012025-04-17 01:04
    Can compressai be installed at 5090d nvidia?
  • Issue comment#335wl3b10s2025-04-03 03:01
    memory usage continue increase for JointAutoregressiveHierarchicalPriors
  • Issue#335wl3b10s2025-04-03 03:01
    memory usage continue increase for JointAutoregressiveHierarchicalPriors
  • Issue comment#335wl3b10s2025-04-02 00:19
    memory usage continue increase for JointAutoregressiveHierarchicalPriors
  • Issue comment#335wl3b10s2025-03-28 06:23
    memory usage continue increase for JointAutoregressiveHierarchicalPriors
  • Issue#335wl3b10s2025-03-28 05:42
    memory usage continue increase for JointAutoregressiveHierarchicalPriors

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 144 stars here means stars gained during the window, not the repo's star count.