Bảng xếp hạng repo GitHub theo sao, tốc độ tăng trưởng và mức độ hoạt động.

• vllm-project

  #1vllm-project/vllm

  A high-throughput and memory-efficient inference and serving engine for LLMs

  Python91.383 saopush cuối 23 giờ trước
• 1Panel-dev

  #21Panel-dev/MaxKB

  🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

  Python22.750 saopush cuối 23 giờ trước
• modelscope

  #3modelscope/ms-swift

  Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

  Python15.567 saopush cuối 2 ngày trước
• qualcomm

  #4qualcomm/GenieX

  Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

  Rust8.358 saopush cuối Hôm qua
• zilliztech

  #5zilliztech/deep-searcher

  Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

  Python8.259 saopush cuối 10 tháng trước
• johnbean393

  #6johnbean393/Sidekick

  A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.

  Swift3.311 saopush cuối 4 tháng trước
• RunanywhereAI

  #7RunanywhereAI/wally

  Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG

  C++1.543 saopush cuối Hôm qua
• syv-ai

  #8syv-ai/qwen38-27b-rtx3090

  Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks

  Python1.238 saopush cuối 3 ngày trước

#	Repo	Ngôn ngữ	Sao	Xu hướng 30 ngày	Cập nhật lần cuối
1	vllm-project vllm-project/vllm A high-throughput and memory-efficient inference and serving engine for LLMs	Python	91.383		push cuối 23 giờ trước
2	1Panel-dev 1Panel-dev/MaxKB 🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。	Python	22.750		push cuối 23 giờ trước
3	modelscope modelscope/ms-swift Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).	Python	15.567		push cuối 2 ngày trước
4	qualcomm qualcomm/GenieX Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code	Rust	8.358		push cuối Hôm qua
5	zilliztech zilliztech/deep-searcher Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.	Python	8.259		push cuối 10 tháng trước
6	johnbean393 johnbean393/Sidekick A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.	Swift	3.311		push cuối 4 tháng trước
7	RunanywhereAI RunanywhereAI/wally Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG	C++	1.543		push cuối Hôm qua
8	syv-ai syv-ai/qwen38-27b-rtx3090 Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks	Python	1.238		push cuối 3 ngày trước

Tất cả · 11.474