dafu-wu's Stars
leondz/garak
LLM vulnerability scanner
InternLM/lmdeploy
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
GitHubDaily/GitHubDaily
坚持分享 GitHub 上高质量、有趣实用的开源技术教程、开发者工具、编程网站、技术资讯。A list cool, interesting projects of GitHub.
andrewyng/translation-agent
traceloop/openllmetry
Open-source observability for your LLM application, based on OpenTelemetry
triton-inference-server/backend
Common source, scripts and utilities for creating Triton backends.
infiniflow/ragflow
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
triton-inference-server/tensorrtllm_backend
The Triton TensorRT-LLM Backend
karpathy/llm.c
LLM training in simple, raw C/CUDA
BradyFU/Awesome-Multimodal-Large-Language-Models
:sparkles::sparkles:Latest Advances on Multimodal Large Language Models
agiresearch/AIOS
AIOS: LLM Agent Operating System
princeton-nlp/SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.
protectai/modelscan
Protection against Model Serialization Attacks
databricks/dbrx
Code examples and resources for DBRX, a large language model developed by Databricks
flexflow/FlexFlow
FlexFlow Serve: Low-Latency, High-Performance LLM Serving
databricks/megablocks
NVIDIA/deepops
Tools for building GPU clusters
xai-org/grok-1
Grok open release
kedacore/keda
KEDA is a Kubernetes-based Event Driven Autoscaling component. It provides event driven scale for any container running in Kubernetes
outlines-dev/outlines
Structured Text Generation
nexusflowai/NexusRaven-V2
rubra-ai/rubra
Open Weight, tool-calling LLMs
uclaml/SPIN
The official implementation of Self-Play Fine-Tuning (SPIN)
OpenNLPLab/lightning-attention
Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
pytorch-labs/gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
yangjianxin1/Firefly
Firefly: 大模型训练工具,支持训练Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型
parallel75/Microsoft_AutoGen_Tutorial
微软 AutoGen 框架 Demo
sgl-project/sglang
SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.
HeKun-NVIDIA/CUDA-Programming-Guide-in-Chinese
This is a Chinese translation of the CUDA programming guide
ray-project/llmperf-leaderboard