Review economics
vllm-project/vllm
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.7× the reviews submitted of the rest.
≥13%
Attributed
a floor
17
Attributed PRs
83
Other PRs
100
Read
Attributed — the latest 5
#51014 [Docs] Fix two docs build warnings
2 reviews · 2h to merge
#51003 [Bugfix][Build] Fix DeepGEMM CUDA 12.9 FP8 header visibility
1 reviews · 1h to merge
#50886 [Bugfix][Reasoning] kimi_k3: O(delta) reasoning-end check on the decode path
2 reviews · 11h to merge
#50567 [Bugfix][Kimi-K3] Enforce packed rows and op availability in AttnRes dispatch
2 reviews · 3.6d to merge
#50926 [CI][Bugfix] Fix flaky `test_store_orders_after_compute_write`
2 reviews · 2h to merge
The rest — the latest 5
#50593 [Kimi-K3][AMD] Fuse AttnRes state updates and norms
2 reviews · 4.0d to merge
#49558 [Bugfix][MoE] Filter packed expert weights during EP loading
2 reviews · 12.4d to merge
#50867 fix: fuse weightless RMSNorms at their declared width
3 reviews · 27h to merge
#38390 [Model Runner v2] E/P/D disaggregation support
13 reviews · 129.9d to merge
#50580 [Frontend] DeepSeek V4 0731 reasoning effort prompts & mappings
1 round · 6 reviews · 4.0d to merge
How this was measured
13% of merged commits carry agent attribution — a floor, not the share; tools that only complete code inline leave no commit trail, so the unattributed side includes AI-assisted work; reads 100 of 19463 merged PRs — the rest have not been analyzed yet.
Detected: OpenAI Codex, Claude Code, Cursor agent.
“Attributed” means a commit carried an agent’s signature — a co-author trailer, an agent commit identity, or an agent bot account. Tools that only complete code inline leave no such mark, so the other column is “rest”, not “human-written”. Full method and its limits
The badge reads this repo’s current report, so it follows the number.
Tell me when this moves
We re-read vllm-project/vllm weekly and email only when the number changes materially.
Read your own repos
This one is public. For a private repo, run the same read locally through your own GitHub credentials — nothing is installed and nothing is sent to us.
npx @ambera/review-taxWant this continuously on vllm-project/vllm — each pull request paired to the task it came from, and the work graded from its review loop rather than its diff size? Claim this repo in Forge
Browse every repo people have read · Read a different repository