Skip to content

vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs

active 2024-11-012026-08-10 (UTC)

Partial coverage16,019 / 19,945 hourly files (80%) · 2 absent upstream · 3,925 failed, retryable2024-05-022026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
1.4K
Pushes
1.1K
Pull requests
7
Issues
48
Stars
6
Forks
1

Activity over time

Daily event counts in the loaded window

Line chart, 648 days from 2024-11-01 to 2026-08-10. Pushes: 1,064 total, peak 19 in a day. Pull requests: 7 total, peak 2 in a day. Issues: 48 total, peak 10 in a day. Comments: 54 total, peak 5 in a day. Stars: 6 total, peak 1 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
vllmellm49947708
tjtanaa43841238
maralbahari535300
github-actions[bot]530033
iAmir97363600
big-yellow-duck232120
BadrBasowid171700
kliuae161600
noobHappylife131300
DarkLight13377700
rbrugaro-amd2002
zyongye1010
jikunshang1001
tanpinsiang1100
xinyu-intel1010

Recent activity

Latest issues, pull requests and releases

  • Pull request#83zyongye2026-05-12 03:49
  • Issue comment#81rbrugaro-amd2026-04-27 06:08
    [ROCm] Use AITER fused_ar_rms API and refine use_1stage heuristic
  • Issue comment#81vllmellm2026-04-24 11:03
    [ROCm] Use AITER fused_ar_rms API and refine use_1stage heuristic
  • Issue comment#81rbrugaro-amd2026-04-21 23:09
    [ROCm] Use AITER fused_ar_rms API and refine use_1stage heuristic
  • Pull request#82xinyu-intel2026-04-21 06:16
  • Issue comment#82jikunshang2026-04-20 23:45
    support fp8 quant vllm ir on xpu
  • Pull request#79big-yellow-duck2026-03-12 08:13
  • Pull request#78big-yellow-duck2026-03-12 06:31
  • Issue#74github-actions[bot]2025-11-22 02:09
    [Bug] [ROCm] [AITER]: ValueError: arange's range must be a power of 2
  • Issue comment#76github-actions[bot]2025-11-17 08:52
    [DO NOT MERGE] Refactor/aiter integration
  • Issue comment#73github-actions[bot]2025-11-13 02:14
    [RFC]: Adding a GH workflow to add label to issues like in PR
  • Issue#75github-actions[bot]2025-10-30 16:04
    [RFC]: Fixing the ViT Backend especially ROCm
  • Issue#75tjtanaa2025-10-30 16:04
    [RFC]: Fixing the ViT Backend especially ROCm
  • Issue#74github-actions[bot]2025-10-22 02:12
    [Bug] [ROCm] [AITER]: ValueError: arange's range must be a power of 2
  • Issue#66github-actions[bot]2025-10-03 02:05
    [Feature]: Optimize ROCm Attention Backend on V1
  • Issue comment#66github-actions[bot]2025-10-03 02:05
    [Feature]: Optimize ROCm Attention Backend on V1
  • Issue comment#29github-actions[bot]2025-09-26 02:07
    [Feature]: Roadmap for 2nd Quarter 2025
  • Issue#29github-actions[bot]2025-09-26 02:07
    [Feature]: Roadmap for 2nd Quarter 2025
  • Issue comment#65github-actions[bot]2025-09-25 02:07
    [Bug]: Fix CompressedTensors FP8 weights accuracy
  • Issue#65github-actions[bot]2025-09-25 02:07
    [Bug]: Fix CompressedTensors FP8 weights accuracy
  • Issue#62github-actions[bot]2025-09-13 02:01
    [Feature]: Integrate AITER MLA V1 from Upstream
  • Issue comment#46github-actions[bot]2025-09-12 02:04
    [Feature]: Enable MLA for V1 on AMD [Triton MLA]
  • Issue#46github-actions[bot]2025-09-12 02:04
    [Feature]: Enable MLA for V1 on AMD [Triton MLA]
  • Issue comment#55github-actions[bot]2025-09-12 02:04
    [Usage]: Document how to use AITER on vLLM
  • Issue comment#64github-actions[bot]2025-09-12 02:04
    [Doc]: Find out about how to optimize the parameters of vLLM V1 on ROCm

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 6 stars here means stars gained during the window, not the repo's star count.