Skip to content

SDAR (Synergy of Diffusion and AutoRegression), a large-scale diffusion language model that unites the complementary strengths of autoregressive and discrete diffusion modeling.

active 2025-08-142026-08-18 (UTC)

Complete coverage26,760 / 26,760 hourly files (100%) · 2 absent upstream2023-08-152026-09-02 (UTC)
Events
221
Pushes
21
Pull requests
0
Issues
19
Stars
140
Forks
8

Activity over time

Daily event counts in the loaded window

Line chart, 370 days from 2025-08-14 to 2026-08-18. Pushes: 21 total, peak 6 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 19 total, peak 3 in a day. Comments: 31 total, peak 3 in a day. Stars: 140 total, peak 16 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#32STAR-CV2025-12-18 06:49
    About inference engine JetEngine
  • Issue comment#31deadlykitten42025-12-17 09:16
    Inquiry about the SFT
  • Issue comment#31deadlykitten42025-12-15 08:57
    Inquiry about the SFT
  • Issue#33chengshuang182025-12-15 03:39
    Questions about AR -> SDAR
  • Issue#33chengshuang182025-12-15 03:39
    Questions about AR -> SDAR
  • Issue comment#33SSSSSSuger2025-12-15 03:23
    Questions about AR -> SDAR
  • Issue comment#32STAR-CV2025-12-12 01:48
    About inference engine JetEngine
  • Issue comment#31chengshuang182025-12-09 06:24
    Inquiry about the SFT
  • Issue comment#21chengshuang182025-12-01 05:03
    Evaluation Pipeline
  • Issue comment#25clf282025-11-30 08:08
    Reproducing Continued Pretraining with LLaMAFactory and qwen3-base
  • Issue comment#27zjr20002025-11-22 04:58
    Question about training loss
  • Issue comment#23armanakbari2025-11-21 19:54
    OOM on 4B model training
  • Issue comment#26chengshuang182025-11-21 07:07
    Training loss crashes when sequence length exceeds 20k
  • Issue#25zjr20002025-11-20 06:37
    Reproducing Continued Pretraining with LLaMAFactory and qwen3-base
  • Issue comment#25chengshuang182025-11-20 03:41
    Reproducing Continued Pretraining with LLaMAFactory and qwen3-base
  • Issue comment#23armanakbari2025-11-19 23:16
    OOM on 4B model training
  • Issue comment#23AlekseyCalvin2025-11-19 21:27
    OOM on 4B model training
  • Issue comment#23chengshuang182025-11-19 12:56
    OOM on 4B model training
  • Issue#18LuLuLuyi2025-11-14 03:15
    OOM Issue When Training SDAR-30B-A3B-Sci
  • Issue#19armanakbari2025-11-08 15:22
    Jetengine error
  • Issue comment#19armanakbari2025-11-08 15:22
    Jetengine error
  • Issue comment#18Labman422025-11-08 03:18
    OOM Issue When Training SDAR-30B-A3B-Sci
  • Issue#20armanakbari2025-11-07 20:54
    Evaluation Code
  • Issue#19armanakbari2025-11-07 15:39
    Jetengine error
  • Issue comment#18LuLuLuyi2025-11-07 08:13
    OOM Issue When Training SDAR-30B-A3B-Sci

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 140 stars here means stars gained during the window, not the repo's star count.