Skip to content

dInfer: An Efficient Inference Framework for Diffusion Language Models

active 2025-10-142026-05-22 (UTC)

Partial coverage11,449 / 12,407 hourly files (92%) · 2 absent upstream · 956 failed, retryable2025-03-112026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
216
Pushes
28
Pull requests
1
Issues
19
Stars
124
Forks
4

Activity over time

Daily event counts in the loaded window

Line chart, 221 days from 2025-10-14 to 2026-05-22. Pushes: 28 total, peak 4 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 19 total, peak 5 in a day. Comments: 35 total, peak 6 in a day. Stars: 124 total, peak 21 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#40superallen132026-04-01 04:03
    New QR Code
  • Issue comment#21xingzhejun2026-01-26 20:17
    Please Update Wechat QR code~ Thank you very much!
  • Issue comment#32AIxyz2026-01-10 09:18
    The traceback of test_bd_serving
  • Issue comment#30zheng-da2026-01-07 12:35
    Feature/threshold remasking
  • Issue comment#31AIxyz2026-01-07 02:30
    Multi thread to curl LLaDA2.0-mini dInfer server will have more and more wrong answer for HumanEval
  • Issue comment#31zheng-da2026-01-06 16:19
    Multi thread to curl LLaDA2.0-mini dInfer server will have more and more wrong answer for HumanEval
  • Issue comment#28AIxyz2025-12-27 03:47
    LLaDA2.0-mini torch error
  • Issue comment#27zheng-da2025-12-26 08:59
    [Feature Request] Support for NPU
  • Issue comment#29Nobody-Zhang2025-12-22 11:32
    Question about benchmarking YAML configurations
  • Issue#28AIxyz2025-12-22 07:58
    LLaDA2.0-mini torch error
  • Issue comment#25AIxyz2025-12-22 03:34
    Is that possible to enable stream output like the other AR model?
  • Issue comment#21lundu282025-12-21 08:32
    Please Update Wechat QR code~ Thank you very much!
  • Issue#27zeus-cht2025-12-21 08:19
    [Feature Request] Support for NPU
  • Issue comment#8lundu282025-12-21 08:13
    How to Reproduce 1000 TPS Results from Paper & Ablation Study Details
  • Issue#1zheng-da2025-12-21 08:06
    Link LLaDA-MoE-7B-A1B-Instruct model to dInfer Paper Page on Hugging Face
  • Issue#9zheng-da2025-12-21 08:05
    Cannot do inference with batch size > 1
  • Issue#24zheng-da2025-12-21 07:57
    vllm and sglang version conflict
  • Issue comment#24zheng-da2025-12-21 07:57
    vllm and sglang version conflict
  • Issue#26czg12252025-12-21 07:56
    Unexpected error for LLaDA2.0-mini moe fusing
  • Issue comment#26czg12252025-12-21 07:56
    Unexpected error for LLaDA2.0-mini moe fusing
  • Issue comment#25zheng-da2025-12-21 07:56
    Is that possible to enable stream output like the other AR model?
  • Issue comment#26zheng-da2025-12-21 07:55
    Unexpected error for LLaDA2.0-mini moe fusing
  • Releasezheng-da2025-12-21 07:11
    v0.2.0
  • Issue#25neoyxm2025-12-16 07:05
    Is that possible to enable stream output like the other AR model?
  • Issue#19zheng-da2025-12-10 05:57
    Does dInfer support OpenAI-Compatible APIs?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 124 stars here means stars gained during the window, not the repo's star count.