Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Community maintained hardware plugin for vLLM on Huawei Ascend

01Result

vllm-project/vllm-ascend ↗

vllm-project/vllm-ascend AI coding statistics: 3.2%

of 2,935 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3.2% agent · top contributor 12.8%53 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

94
agent commits
2,841
other considered commits
53
agent contributors
12.8%
largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

94assisted
0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-020.6%162
2026-031.4%345
2026-042.8%289
2026-051.8%279
2026-063.9%487
2026-072.6%539
2026-082.7%484
2026-098.3%350

Peak month: 8.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere341.2%
Gemini CLIGoogle341.2%
Claude CodeAnthropic260.9%
GitHub CopilotGitHub10%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

  • a53bd9ca on GitHub[BugFix] [KV Pool]: forward child connector KV cache events (#16408)Cursor Agent
  • a643db11 on GitHub[Test]ut test case coverage improvement added. (#16239)Cursor Agent
  • 0b345a67 on GitHub[CI]Added and modified E2E test cases for precise testing. (#15423)Cursor Agent
  • 2d5e56e0 on GitHub[Performance] Fuse index+copy into single out= gather in get_cos_and_sin_dGemini CLI
  • baa2ac75 on GitHub[Refactor][Worker] Retire redundant worker patches (#14528)Gemini CLI
  • 0a023b09 on GitHub[Feature][Model] Add Kimi K3 support for vLLM 0.27 (#14454)Gemini CLI
  • b246529e on GitHub[Feature][Kimi K3 DSPark] Enable TP for context_proj (#16344)Claude Code
  • ffc2112d on GitHub[Feature]Gemma MTP speculative decoding support on Ascend NPU A5 (#13045)Claude Code
  • 7a7d60e3 on GitHub[Doc][Misc] Sync GLM5 and GLM-5.2 tutorials from releases/v0.26.0rc (#1588Claude Code
  • 849a92e6 on GitHub[Bugfix][DSV4] Enhance QLI workspace size calculation for ASCEND 950 (#100GitHub Copilot

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window2,966
Merge commits removed−0
CI / dependency bots removed−31
Considered2,935

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Gemini CLI commitsBrowse repositories with detected Gemini CLI signatures →Python AI coding statisticsCompare evidence across Python repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →
Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli vllm-project/vllm-ascend

Scan another repository

Try