Skip to content

High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

active 2025-07-032026-01-09 (UTC)

Complete coverage26,593 / 26,593 hourly files (100%) · 2 absent upstream2023-08-152026-08-27 (UTC)
Events
419
Pushes
210
Pull requests
63
Issues
0
Stars
0
Forks
1

Activity over time

Daily event counts in the loaded window

Line chart, 191 days from 2025-07-03 to 2026-01-09. Pushes: 210 total, peak 16 in a day. Pull requests: 63 total, peak 5 in a day. Issues: 0 total, peak 0 in a day. Comments: 55 total, peak 11 in a day. Stars: 0 total, peak 0 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
fmiao23721551102115
LeoZhao-Intel75221415
yanfeich5132126
JianyuLi01211065
github-actions[bot]191900
feiwan19351
FocusLuo2000
EmmonsCurse1100

Recent activity

Latest issues, pull requests and releases

  • Pull request#61fmiao23722025-12-03 05:33
  • Issue comment#60yanfeich2025-11-26 05:45
    MoE weights and scales from list to tensor
  • Pull request#60yanfeich2025-11-25 11:36
  • Pull request#59feiwan12025-11-25 07:44
  • Issue comment#57JianyuLi012025-11-25 07:28
    Support Qwen3 MoE
  • Pull request#54fmiao23722025-11-07 03:28
  • Pull request#53fmiao23722025-11-06 06:32
  • Issue comment#52feiwan12025-11-06 05:53
    Update to new interface of fused_block_attention OP
  • Pull request#51LeoZhao-Intel2025-11-04 07:11
  • Pull request#47LeoZhao-Intel2025-09-28 07:05
  • Issue comment#47fmiao23722025-09-28 07:02
    add bench_gsm8k script and test jsonl
  • Issue comment#47LeoZhao-Intel2025-09-28 06:59
    add bench_gsm8k script and test jsonl
  • Pull request#47LeoZhao-Intel2025-09-28 06:59
  • Pull request#44fmiao23722025-09-22 08:34
  • Pull request#46LeoZhao-Intel2025-09-19 06:25
  • Issue comment#44yanfeich2025-09-17 02:49
    [Intel HPU] Support intel hpu platform
  • Pull request#45JianyuLi012025-09-12 10:16
  • Pull request#44fmiao23722025-09-12 03:13
  • Pull request#44fmiao23722025-09-12 03:11
  • Pull request#43yanfeich2025-09-12 00:57
  • Pull request#43yanfeich2025-09-12 00:57
  • Pull request#42yanfeich2025-09-11 09:10
  • Issue comment#42yanfeich2025-09-11 08:59
    fix multicards weight load issue
  • Pull request#42yanfeich2025-09-11 08:56
  • Issue comment#41JianyuLi012025-09-11 07:52
    Fused Sampler (all hpus do the same work)

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.