Creators

vllm-project

vllm-projectFirst product launched 3y ago

Total monthly visits
790.9K
Down22.2%MoMOct 2026
ARR
$2,554Verified
≈ $212.83/mo · Open Collective · 2026-11-20“USD 2,554/yr (Open Collective transparent ledger) · 来源:Open Collective Ledger”
Products
1
Since Jun 2023
Latest launch
3y ago
vLLM790.9K visits/mo · $2,554/yr (verified)
100% full-depth creator dossier open: complete product portfolio, 12-month combined traffic & MRR curves, shipping cadence, and timeline events.

Traffic & revenue

Portfolio · Last 12 months
Monthly visits
Monthly revenue & equivalents1 / 1 products with revenue evidence
Nov 2026
vLLM$213/moSelf-reported eq.

Products

Products and research metrics
ProductVisits · OctActions
vLLMOSSThe High-Throughput and Memory-Efficient inference and serving engine for LLMs790.9K

Timeline

Launches, marketing, revenue milestones, and pricing/plan/positioning changes across products
  1. Nov 20 · Yesterday

    • vLLM disclosed ARR $2,554Verified revenue

      Open Collective

  2. Nov 18 · 3d ago

    • vLLM releases v0.34.0 with 10 new models and default extensible KV cacheProduct Activity

      vLLM released v0.34.0 with 1,061 commits from 412 contributors and support for 10 new models. Extensible KV cache is enabled by default, and Model Runner V2 is now the only GPU runner. The announcement reports up to 1.95× faster Step5 NVFP4 decode on 4× GB200.

    • vLLM adds day-0 support for Tencent's Hy4 flashProduct Activity

      vLLM announced day-0 support for Tencent's Hy4 flash, a multimodal model with a 1M-token context. It says the model can run on NVIDIA GPUs with vLLM and provides a release image and deployment recipe; the integration work was by Inferact.

  3. Nov 17 · 4d ago

    • vLLM solicits feedback on its Q4 2026–Q1 2027 roadmapPromotions

      vLLM asks users to rate needed features, identify missing features, or propose a new work group. It says feedback will set priorities for upcoming releases and links to a feedback form.

    • vLLM updates DSpark support for Kimi K3.1 Pro speculative decodingProduct Activity

      vLLM says the new DSpark for Kimi K3.1 Pro was jointly developed by Inferact and the Red Hat AI Speculators team with vLLM and Speculators. It reports up to 30% higher acceptance length than the preview on HumanEval and a 2K sliding window in each draft layer to bound draft KV memory at 1M-token context. vLLM also describes redesigned KV management supporting P/D disaggregation and different parallelism configurations to bring sliding-window draft models into production.

Questions & evidence

What products has vllm-project built?
vllm-project tracks 1 standalone software products on EarlyLore (1 currently live), led by vLLM.
How much website traffic do vllm-project's products get?
Across tracked standalone domains with web traffic estimates, vllm-project's portfolio reaches 790.9K combined monthly visits in each site's latest observed month. Coverage excludes shared third-party hosts and store listings.

Related indie founder research guides