GitHub Hot Board · Arsip repositori
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-2.0Aktif dirawat · Push 5 hari lalu#consumer-gpu#cuda#inference-optimization#kv-cache#llm-inference#local-llm#quantization#qwen
Star
2.6k
Fork
332
Issue
15
Kenaikan harian
—
hari
3d
6-Axis Combat Radar
Combat Limits & Architectural Persona
Architectural Persona
Specialized Tactical Vanguard
Distinct edge and dedicated footprint in specialized territory
Combat Score
61
/ 100
7-Day Star Velocity
0
Fork/Star Adoption
12.7%
Jumlah bintang kumulatif
Next Milestone: 5k (2.4k stars to go)+80 (3d)2026-11-08: 2.6k
Kenaikan harian
Max: +72 / day
Proyek serupa · topik bersama
Studio Lencana Pengelola
Sematkan Lencana Langsung di README GitHub
Sematkan lencana SVG dinamis ke README Anda untuk menampilkan peringkat waktu nyata dan tautan dokumentasi.
Pratinjau240 x 64 px SVG
GitHub Dark Theme
GitHub Light Theme