Skip to content

minimal reimplementation of deepmind's genie 3 world model

Python · active 2025-09-212026-06-18 (UTC)

Partial coverage11,566 / 12,653 hourly files (91%) · 2 absent upstream · 1,083 failed, retryable2025-03-012026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
684
Pushes
12
Pull requests
5
Issues
9
Stars
580
Forks
43

Activity over time

Daily event counts in the loaded window

Line chart, 271 days from 2025-09-21 to 2026-06-18. Pushes: 12 total, peak 2 in a day. Pull requests: 5 total, peak 2 in a day. Issues: 9 total, peak 2 in a day. Comments: 32 total, peak 8 in a day. Stars: 580 total, peak 136 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#20eren232026-04-13 09:28
    feat: add MoE SwiGLU FFN and Muon optimizer
  • Issue#19AlmondGod2026-04-13 04:29
    action annotations
  • Issue comment#16AlmondGod2026-03-22 04:20
    feat: replace action tokenizer with windowed attention
  • Issue comment#14GYXXXXXX2026-01-23 09:12
    Problems when directly running inference
  • Issue comment#14AlmondGod2026-01-20 21:50
    Problems when directly running inference
  • Issue comment#16AlmondGod2026-01-20 21:47
    feat: replace action tokenizer with windowed attention
  • Issue comment#14GYXXXXXX2026-01-20 06:21
    Problems when directly running inference
  • Issue comment#14pedrohenriquebr2026-01-06 02:12
    Problems when directly running inference
  • Issue comment#15AlmondGod2025-11-27 07:26
    dataset
  • Issue#15wangsiyu6662025-11-27 06:37
    dataset
  • Issue#7AlmondGod2025-11-22 23:16
    Set TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information
  • Issue comment#10AlmondGod2025-11-22 23:16
    Can you also mention the GPU config this is trained on?
  • Issue comment#14AlmondGod2025-11-22 23:15
    Problems when directly running inference
  • Issue comment#12AlmondGod2025-11-22 23:14
    Fix error with gradient_accumulation_steps > 1 by calling cudagraph_mark_step_begin()
  • Pull request#13SeanNobel2025-11-14 07:54
  • Pull request#12SeanNobel2025-11-14 07:23
  • Issue comment#11alekseymalakhov112025-11-08 06:24
    🚀 Add FSDP2 support
  • Issue comment#11AlmondGod2025-11-08 01:39
    🚀 Add FSDP2 support
  • Issue comment#11alekseymalakhov112025-11-06 21:15
    🚀 Add FSDP2 support
  • Issue comment#11alekseymalakhov112025-11-05 00:26
    🚀 Add FSDP2 support
  • Issue comment#5Scriptwonder2025-10-30 16:54
    Error: num_frames got 0
  • Pull request#11alekseymalakhov112025-10-29 18:47
  • Issue#10aman1902022025-10-25 21:17
    Can you also mention the GPU config this is trained on?
  • Issue comment#5mkemka2025-10-04 01:52
    Error: num_frames got 0
  • Issue comment#7Natyren2025-10-03 19:18
    Set TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 580 stars here means stars gained during the window, not the repo's star count.