1.vllm-project / vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
+593 stars
from 95,485 · score 6.39
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
10 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2.mw00 / project-maya
Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
+512 stars
from 1,865 · score 6.24
3.sgl-project / sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
+192 stars
from 38,156 · score 5.26
4.hiyouga / LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
+96 stars
from 75,728 · score 4.57
5.FareedKhan-dev / kimi-k3-in-c
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
+89 stars
from 9,186 · score 4.50
6.Indras-Mirror / Xolotl
Xolotl (formerly Strata-DSV4.1): run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 90 GB RAM) at up to ~27 tok/s, 512K context, October 1017 builds included. Plus GLM-5.3-Flash and Qwen3.8. MoE experts tiered across VRAM, pinned RAM and NVMe; OpenAI + Anthropic API.
+80 stars
from 356 · score 4.39
7.modelscope / 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
8.carloslfu / slotstream
Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.
+71 stars
from 569 · score 4.28
9.NVIDIA / TensorRT-LLM
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
+42 stars
from 14,945 · score 3.76
10.YeonwooSung / llm-architecture-from-scratch
Implementing LLM architectures from scratch in PyTorch
+4 stars
from 1,105 · score 1.61