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.
≥15%
Attributed
a floor
24
Attributed PRs
76
Other PRs
100
Read
Attributed — the latest 5
#44359 [MoE] Share apply_moe_activation support metadata
7 reviews · 63.9d to merge
#51067 [Docker][KVConnector] Install mooncake from official wheels instead of a custom build
4 reviews · 24h to merge
#50358 [Bugfix] Fail fast with a clear error when CPU offload region exceeds available space
1 round · 11 reviews · 6.7d to merge
#51095 [CI] Fix CI authorization notification fallback
1 reviews · 7h to merge
#42436 fused_moe: add VLLM_TRITON_USE_TD tensor-descriptor path
8 reviews · 77.5d to merge
The rest — the latest 5
#48061 [BugFix][Mooncake] Use global data_parallel_index for the DP engine index
3 reviews · 27.0d to merge
#51074 [CI] Prune PyTorch Fullgraph Test
1 reviews · 23h to merge
#51177 [CI Bug] Fix `Chunked prefill is required for mamba cache mode 'align'.`
4 reviews · 2h to merge
#51176 Revert [Misc] Avoid importing `nixl_ep` on every `vllm serve` config (#50879)
3 reviews · 2h to merge
#51180 [CI bug] Fix `Each KV cache group's real block_size must be divisible by has h_block_size`
2 reviews · 1h to merge
How this was measured
15% 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 19516 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, OpenAI Codex.
“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