RepoRadar
Leave a Tip
Item detail

weicj/vLLM-2080Ti-Definitive

vLLM 2080 Ti Definitive Edition weicj/vLLM-2080Ti-Definitive is an Apache-2.0 hardware-focused vLLM fork for dual RTX 2080 Ti / SM75 serving, preserves the patched source, launch profiles, and runtime notes needed to reproduce the working 2080 Ti vLLM stack, ships fork release v0.1.10 on top of base vLLM 0.21.0, claims Qwen3.6 27B reaches 100+ tok/s single-request decode on the dual 2080 Ti TP=2 r

Open source →Back to radar
Score7.9
Popularity261.0
Risklow
TierSilver
Score breakdown
Usefulness8.3
Novelty10.0
Momentum10.0
Maturity8.2
Open-source/build7.4
Evidence7.2
Workflow potential8.6
Setup ease6.5

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for ML infrastructure engineers, inference engineers, AI engineers, indie hackers, hobbyists, and small teams who run dual RTX 2080 Ti GPUs (with NVLink) and want a working vLLM runtime that turns legacy Turing silicon into a credible 27B-class local inference platform at about half the secondary-market price of a single RTX 3090 Ti, because weicj/vLLM-2080Ti-Definitive is an Apache-2.0 har

Who should use it

BuildersPower users

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

Risk label needs manual review.

Evidence links

Closest alternatives / related signals

  • No close related item is available in the current public catalog.