weicj/vLLM-2080Ti-Definitive

vLLM-2080Ti-Definitive

✅ Recently maintained

The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with maximum 200+ tok/s single-request decode with support of FP8 weight ( Join Discord :https://discord.gg/VFqVVySdMS )

1,200Stars
167Forks
+147-day stars

Python · Apache-2.0 · Last push 2026-10-01

Official repository & installation ↗

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2026-06-012026-11-02
View historical data
DateStars
2026-10-041,084
2026-10-051,090
2026-10-061,098
2026-10-071,102
2026-10-081,109
2026-10-091,113
2026-10-101,118
2026-10-111,124
2026-10-121,131
2026-10-131,135
2026-10-141,140
2026-10-151,148
2026-10-161,153
2026-10-171,156
2026-10-181,159
2026-10-191,163
2026-10-201,168
2026-10-211,171
2026-10-221,172
2026-10-231,175
2026-10-241,179
2026-10-251,182
2026-10-261,185
2026-10-271,187
2026-10-281,189
2026-10-291,192
2026-10-301,194
2026-10-311,195
2026-11-011,195
2026-11-021,200

Get the project

git clone https://github.com/weicj/vLLM-2080Ti-Definitive.git

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.