Neural Network Compression Framework for enhanced OpenVINO™ inference
GitHub repository with 1,169 stars and 294 forks.
Language: Python
Topics: quantization, pruning, sparsity, quantization-aware-training, mixed-precision-training, compression, semantic-segmentation, object-detection, classification, nlp
2026-06-05: 1,169 stars and 294 forks.
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.
GitHub repository with 279 stars and 10 forks.
Trending score: 1.84; stars gained: +75; forks gained: +4.
Language: Python
Topics: agentic-ai, kv-cache, llm, llm-inference, long-context, quantization
A vector index built on TurboQuant, written in Rust with Python bindings
GitHub repository with 4,086 stars and 389 forks.
Trending score: 1.70; stars gained: +63; forks gained: +9.
Language: Python
Topics: ann, avx512, embeddings, faiss, nearest-neighbor, neon
A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.
GitHub repository with 1,436 stars and 135 forks.
Trending score: 1.06; stars gained: +6; forks gained: +0.
Language: Python
Topics: int4, quantization, rounding, transformers, vllm, mxfp4
W8A8/W4A8 inference + optimized SDPA on Apple Silicon — unlocking unused INT8 TensorOps in M5 for 1.2–1.9× faster LLM prefill, plus FlashInfer-inspired GQA decode attention for up to 1.6× SDPA speedup, built as MLX custom primitives.
GitHub repository with 324 stars and 15 forks.
Trending score: 0.83; stars gained: +6; forks gained: +0.
Language: Python
Topics: apple-silicon, metal, mlx, quantization, w4a8, w8a8
PyTorch native quantization and sparsity for training and inference
GitHub repository with 2,846 stars and 515 forks.
Trending score: 0.65; stars gained: +3; forks gained: +2.
Language: Python
Topics: brrr, dtypes, inference, mx, pytorch, quantization
Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — auto-generated by the ARIS /render-html workflow into single-file HTML, reads anywhere — plus a CV→DBLP-fact-checked academic homepage generator and long-form blogs/surveys 🌱
GitHub repository with 167 stars and 6 forks.
Trending score: 0.59; stars gained: +3; forks gained: +0.
Language: Python
Topics: ai-interview, aris, autumn-recruiting, cheatsheet, chinese, claude-code
The agent that grows with you
GitHub repository with 182,659 stars and 31,317 forks.
Trending score: 5.95; stars gained: +1,867; forks gained: +361.
Language: Python
Topics: ai, ai-agent, ai-agents, anthropic, chatgpt, claude
Academic Research Skills for Claude Code: research → write → review → revise → finalize
GitHub repository with 27,643 stars and 2,276 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 28,711 stars and 4,695 forks.
Trending score: 5.32; stars gained: +1,261; forks gained: +238.
Language: Python
Topics: agents, ai, ai-agents, ai-engineering, computer-vision, course
An opinionated list of Python frameworks, libraries, tools, and resources
GitHub repository with 301,435 stars and 28,046 forks.
Trending score: 4.60; stars gained: +518; forks gained: +24.
Language: Python
Topics: awesome, collections, python, python-frameworks, python-libraries, python-tools
Use claude-code for free in the terminal, VSCode extension or discord like OpenClaw (voice supported)
GitHub repository with 32,540 stars and 4,942 forks.
Trending score: 4.56; stars gained: +467; forks gained: +82.
Language: Python
The agent engineering platform.
GitHub repository with 138,587 stars and 22,961 forks.
Trending score: 4.53; stars gained: +171; forks gained: +31.
Language: Python
Topics: agents, ai, ai-agents, anthropic, chatgpt, deepagents
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.
GitHub repository with 279 stars and 10 forks.
Trending score: 1.84; stars gained: +75; forks gained: +4.
Language: Python
Topics: agentic-ai, kv-cache, llm, llm-inference, long-context, quantization
A vector index built on TurboQuant, written in Rust with Python bindings
GitHub repository with 4,086 stars and 389 forks.
Trending score: 1.70; stars gained: +63; forks gained: +9.
Language: Python
Topics: ann, avx512, embeddings, faiss, nearest-neighbor, neon
Camelid: a Rust-native local inference backend with evidence-gated model compatibility.
GitHub repository with 53 stars and 10 forks.
Trending score: 1.25; stars gained: +17; forks gained: +2.
Language: Rust
Topics: apple-silicon, gguf, inference, llama, llm, local-first
A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.
GitHub repository with 1,436 stars and 135 forks.
Trending score: 1.06; stars gained: +6; forks gained: +0.
Language: Python
Topics: int4, quantization, rounding, transformers, vllm, mxfp4
W8A8/W4A8 inference + optimized SDPA on Apple Silicon — unlocking unused INT8 TensorOps in M5 for 1.2–1.9× faster LLM prefill, plus FlashInfer-inspired GQA decode attention for up to 1.6× SDPA speedup, built as MLX custom primitives.
GitHub repository with 324 stars and 15 forks.
Trending score: 0.83; stars gained: +6; forks gained: +0.
Language: Python
Topics: apple-silicon, metal, mlx, quantization, w4a8, w8a8
PyTorch native quantization and sparsity for training and inference
GitHub repository with 2,846 stars and 515 forks.
Trending score: 0.65; stars gained: +3; forks gained: +2.
Language: Python
Topics: brrr, dtypes, inference, mx, pytorch, quantization