A high-performance attention mechanism that computes softmax normalization in a single streaming pass using running accumulators (online softmax).
GitHub repository with 31 stars and 0 forks.
Language: Python
Topics: cuda, llms, rl, triton
2026-06-05: 31 stars and 0 forks.
A high-throughput and memory-efficient inference and serving engine for LLMs
GitHub repository with 81,995 stars and 17,676 forks.
Trending score: 3.75; stars gained: +79; forks gained: +46.
Language: Python
Topics: amd, blackwell, cuda, deepseek, deepseek-v3, gpt
A GPU cluster manager that configures and orchestrates inference engines like vLLM and SGLang for high-performance AI model deployment.
GitHub repository with 5,107 stars and 542 forks.
Trending score: 2.51; stars gained: +11; forks gained: +1.
Language: Python
Topics: ascend, cuda, deepseek, distributed-inference, genai, high-performance-inference
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
GitHub repository with 8,422 stars and 1,246 forks.
Trending score: 2.17; stars gained: +11; forks gained: +6.
Language: Python
Topics: amd, cuda, fast, inference, kv-cache, llm
SGLang is a high-performance serving framework for large language models and multimodal models.
GitHub repository with 28,860 stars and 6,348 forks.
Trending score: 1.72; stars gained: -55; forks gained: +18.
Language: Python
Topics: attention, blackwell, cuda, deepseek, diffusion, glm
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.
GitHub repository with 13,807 stars and 2,440 forks.
Trending score: 1.18; stars gained: +16; forks gained: +7.
Language: Python
Topics: blackwell, cuda, llm-serving, moe, pytorch
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
GitHub repository with 3,380 stars and 739 forks.
Trending score: 1.10; stars gained: +1; forks gained: +3.
Language: Python
Topics: cuda, deep-learning, gpu, machine-learning, python, pytorch
The agent that grows with you
GitHub repository with 181,939 stars and 31,220 forks.
Trending score: 5.95; stars gained: +1,867; forks gained: +361.
Language: Python
Topics: ai, ai-agent, ai-agents, anthropic, chatgpt, claude
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
GitHub repository with 13,768 stars and 870 forks.
Trending score: 5.69; stars gained: +2,829; forks gained: +175.
Language: Python
Topics: agent, ai, anthropic, compression, context-engineering, context-window
Academic Research Skills for Claude Code: research → write → review → revise → finalize
GitHub repository with 27,537 stars and 2,264 forks.
Trending score: 5.52; stars gained: +1,079; forks gained: +89.
Language: Python
Topics: academic-pipeline, academic-writing, ai-research, claude, claude-code, literature-review
Learn it. Build it. Ship it for others.
GitHub repository with 28,622 stars and 4,680 forks.
Trending score: 5.32; stars gained: +1,261; forks gained: +238.
Language: Python
Topics: agents, ai, ai-agents, ai-engineering, computer-vision, course
GitHub repository with 30,060 stars and 4,235 forks.
Trending score: 4.88; stars gained: +688; forks gained: +114.
Language: Python
An opinionated list of Python frameworks, libraries, tools, and resources
GitHub repository with 301,396 stars and 28,042 forks.
Trending score: 4.60; stars gained: +518; forks gained: +24.
Language: Python
Topics: awesome, python, collections, python-frameworks, python-libraries, python-tools
A high-throughput and memory-efficient inference and serving engine for LLMs
GitHub repository with 81,995 stars and 17,676 forks.
Trending score: 3.75; stars gained: +79; forks gained: +46.
Language: Python
Topics: amd, blackwell, cuda, deepseek, deepseek-v3, gpt
A GPU cluster manager that configures and orchestrates inference engines like vLLM and SGLang for high-performance AI model deployment.
GitHub repository with 5,107 stars and 542 forks.
Trending score: 2.51; stars gained: +11; forks gained: +1.
Language: Python
Topics: ascend, cuda, deepseek, distributed-inference, genai, high-performance-inference
Fast LLM speculative inference server for consumer hardware.
GitHub repository with 2,332 stars and 217 forks.
Trending score: 2.31; stars gained: +17; forks gained: +3.
Language: C++
Topics: kernel, llama-cpp, local-ai, nvidia-cuda, qwen, rtx3090
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
GitHub repository with 8,422 stars and 1,246 forks.
Trending score: 2.17; stars gained: +11; forks gained: +6.
Language: Python
Topics: amd, cuda, fast, inference, kv-cache, llm
Making it easier to work with shaders
GitHub repository with 5,349 stars and 451 forks.
Trending score: 2.08; stars gained: +4; forks gained: +2.
Language: C++
Topics: shaders, hlsl, glsl, d3d12, vulkan, cuda
:metal: TT-NN operator library, and TT-Metalium low level kernel programming model.
GitHub repository with 1,494 stars and 480 forks.
Trending score: 1.82; stars gained: +7; forks gained: +5.
Language: C++
Topics: accelerator, ai, cuda, deepseek, gpu, img-gen