DepthAnything/Video-Depth-Anything
Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
Language: Python
#depth_estimation #monocular_depth_estimation #transformer #video_depth
Stars: 234 Issues: 2 Forks: 8
https://github.com/DepthAnything/Video-Depth-Anything

MoonshotAI/MoBA
MoBA: Mixture of Block Attention for Long-Context LLMs
Language: Python
#flash_attention #llm #llm_serving #llm_training #moe #pytorch #transformer
Stars: 521 Issues: 2 Forks: 16
https://github.com/MoonshotAI/MoBA

therealoliver/Deepdive-llama3-from-scratch
Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.
Language: Jupyter Notebook
#attention #attention_mechanism #gpt #inference #kv_cache #language_model #llama #llm_configuration #llms #mask #multi_head_attention #positional_encoding #residuals #rms #rms_norm #rope #rotary_position_encoding #swiglu #tokenizer #transformer
Stars: 388 Issues: 0 Forks: 28
https://github.com/therealoliver/Deepdive-llama3-from-scratch

yassa9/qwen600
Static suckless single batch CUDA-only qwen3-0.6B mini inference engine
Language: Cuda
#cuda #cuda_programming #gpu #llamacpp #llm #llm_inference #qwen #qwen3 #transformer
Stars: 287 Issues: 1 Forks: 17
https://github.com/yassa9/qwen600

divagr18/memlayer
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory and recall to any model in minutes.
Language: Python
#agent #ai #ai_infrastructure #context_management #developer_tools #embedded #graph_database #knowledge_graph #llm #llm_memory #memory #openai #persistent_memory #python #rag #retrieval #retrieval_augmented_generation #semantic_search #transformer #vector_database
Stars: 175 Issues: 3 Forks: 19
https://github.com/divagr18/memlayer