GitHub Hot Board · Repo-Archiv

syv-ai/hyperqwen

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.

PythonApache-2.0Aktiv gepflegt · Vor 5T gepusht#consumer-gpu #cuda #inference-optimization #kv-cache #llm-inference #local-llm #quantization #qwen

DokumentationAuf GitHub öffnen

Sterne

2.6k

Forks

332

Issues

Tägliche Sterne

—

Tage alt

6-Axis Combat Radar

Combat Limits & Architectural Persona

Compare with other repos ->

Architectural Persona

Specialized Tactical Vanguard

Distinct edge and dedicated footprint in specialized territory

Combat Score

/ 100

7-Day Star Velocity

Fork/Star Adoption

12.7%

Kumulierte Sterne

Next Milestone: 5k (2.4k stars to go)+80 (3d)

2026-11-08: 2.6k

Tägliche Sterne

Max: +72 / day

GitHub README Live-Badge einbetten

Bette dynamische SVG-Badges in deine README ein, um Echtzeit-Rankings und Dokumentationsspiegel zu verlinken.

Vorschau240 x 64 px SVG

GitHub Dark Theme

GitHub Light Theme

GitHub README <picture> (Auto Dark/Light)

<a href="https://git.zoyku.com/de/repo/syv-ai/hyperqwen" target="_blank" rel="noopener noreferrer">
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset="https://git.zoyku.com/api/badge/card/syv-ai/hyperqwen?theme=dark&lang=de" />
    <img alt="GitHub Hot Rank - syv-ai/hyperqwen" src="https://git.zoyku.com/api/badge/card/syv-ai/hyperqwen?theme=light&lang=de" height="64" />
  </picture>
</a>

syv-ai/hyperqwen

Combat Limits & Architectural Persona

Kumulierte Sterne

Ähnliche Projekte · gemeinsame Topics

GitHub README Live-Badge einbetten