GitHub Hot Board · Archive du dépôt

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-2.0Actif & fréquent · Mis à jour il y a 5j#consumer-gpu #cuda #inference-optimization #kv-cache #llm-inference #local-llm #quantization #qwen

DocumentationOuvrir sur GitHub

stars

2.6k

forks

332

issues

Gain quotidien

—

jours d’existence

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%

Étoiles cumulées

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

2026-11-08: 2.6k

Gain quotidien

Max: +72 / day

Projets similaires · sujets partagés

public-apis/public-apis497.3k ebookfoundation/free-programming-books401.3k donnemartin/system-design-primer377.3k vinta/awesome-python333.4k practical-tutorials/project-based-learning289.3k nousresearch/hermes-agent261.7k

Studio de Badges pour Mainteneurs

Intégrer le badge direct au README GitHub

Intégrez des badges SVG dynamiques dans votre README pour afficher vos classements en temps réel et votre miroir de documentation.

Aperçu240 x 64 px SVG

GitHub Dark Theme

GitHub Light Theme

GitHub README <picture> (Auto Dark/Light)

<a href="https://git.zoyku.com/fr/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=fr" />
    <img alt="GitHub Hot Rank - syv-ai/hyperqwen" src="https://git.zoyku.com/api/badge/card/syv-ai/hyperqwen?theme=light&lang=fr" height="64" />
  </picture>
</a>