1lyramakesmusic / neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
+740 stars
from 1,062 · score 6.61
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
12 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2vllm-project / vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
+593 stars
from 95,485 · score 6.39
3unslothai / unsloth
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
+365 stars
from 78,561 · score 5.90
4huggingface / transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
+259 stars
from 168,161 · score 5.56
5syv-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.
+243 stars
from 2,231 · score 5.50
6sgl-project / sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
+192 stars
from 38,156 · score 5.26
7shuishuipingan / qoder2api-hub
Qoder国际国内多账号反代网关，Qoder 国际国内双区多账号 OpenAI 兼容网关中枢 — COSY 签名推理、稳定设备指纹防风控、OAuth 设备授权免客户端登录、每日签到与 Pro 福利、后台定时调度器、Web 监控看板，支持 Codex / Claude Code 与标准 OpenAI 客户端
+114 stars
from 378 · score 4.74
8hiyouga / LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
+96 stars
from 75,728 · score 4.57
9MemTensor / MemT-1.0
Official repository for MemT-1.0
+87 stars
from 398 · score 4.48
10modelscope / ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
+77 stars
from 15,931 · score 4.36
11OpenPipe / ART
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
+15 stars
from 10,821 · score 2.77
12chatchat-space / Langchain-Chatchat
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain
+7 stars
from 38,704 · score 2.08