vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
repoDatacentres 0.9
In cascades:
- → category beneficiary datacentresInference-stack maturity expands deployable GPU demand.
Score
Momentum
91
Divergence
—
30d momentum
—
Components — cohort repo:datacentres
| Family | Velocity 7d | z | Weight | Source |
|---|---|---|---|---|
| code | 3 | +2.26 | 0.25 | gh_stars |
| models | missing | |||
| apps | missing | |||
| hiring | missing | |||
| sdk | missing | |||
| attention | missing |
Memos (0)
No memo yet — run pnpm memo 175.
Metrics (30d)
codegh_stars
latest 86.3k