vLLM
Every number here is named for what it counts. How each one is measured is on the methodology page.
Fig. 1vLLM's share of Hacker News and Lobsters stories, by month
vLLM%
Distinct stories naming the tool, as a percentage of all stories naming any tracked tool. Complete months only.
Fig. 2PyPI downloads a week: vllm
vllm
Each week's median of the daily snapshots, so one glitched snapshot cannot move the line. Complete weeks only.
Job ads naming it, by week
Postings in Adzuna's UK IT feed and on RemoteOK whose title or description names vLLM. Small counts: read the direction, not the rate.
- 10 Aug 0
- 17 Aug 0
- 24 Aug 0
- 31 Aug 0
- 7 Sept 0
- 14 Sept 0
- 21 Sept 0
- 28 Sept 0
- 5 Oct 0
- 12 Oct 0
- 19 Oct 0
- 26 Oct 0
Biggest stories, last 90 days
- Fixing Tool-Call Accuracy in vLLM172 pts · 71 comments · 26 Oct
- Inside vLLM: Anatomy of a High-Throughput LLM Inference System (2025)146 pts · 10 comments · 6 Aug
- Speculative Decoding in vLLM on AMD GPUs143 pts · 53 comments · 7 Sept
- vLLM v0.28.0107 pts · 42 comments · 29 Aug
- Hyper Optimizing Kimi K3 in vLLM30 pts · 0 comments · 18 Oct
- Self-hosted inference orchestrators compared: LocalAI, exo, GPUStack, vLLM11 pts · 2 comments · 20 Sept
- vLLM Recipes4 pts · 0 comments · 4 Aug
- Push-based KV transfer to improve TTFT, TPOT for disaggregated inference in vLLM3 pts · 0 comments · 20 Oct
Bets on vLLM
No calls made on vLLM yet.