1.SYSTRAN / faster-whisper
Faster Whisper transcription with CTranslate2
+724 stars
from 25,650 · score 6.59
Trending repositories
Ranked by Attention Score: stars gained over the last 30 complete days
6 repositories by Attention Score · Oct 4, 2026 – Nov 2, 2026 (UTC)
2.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.
+662 stars
from 1,812 · score 6.50
3.hiyouga / LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
+615 stars
from 75,209 · score 6.42
4.Xilinx / finn
Dataflow compiler for QNN inference on FPGAs
+13 stars
from 1,074 · score 2.64
5.ymcui / Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
+8 stars
from 18,914 · score 2.20
6.google / qkeras
QKeras: a quantization deep learning library for Tensorflow Keras
+1 stars
from 584 · score 0.69