1-day current streak·3-day longest streak
-
Awesome-Attention-Sink ★ PINNED
🚀 First survey on Attention Sink in Transformers — 200+ papers on utilization, interpretation, and mitigation.
★ 132 1mo agoExplain → -
Super-Experts-Profilling ★ PINNED
(ICLR 2026) Unveiling Super Experts in Mixture-of-Experts Large Language Models
Python ★ 42 9mo agoExplain → -
OScaR-KV-Quant ★ PINNED
🏆 OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond — redefining the accuracy-efficiency Pareto front for X-LLMs KV quantization.
C++ ★ 138 1mo agoExplain → -
SGLang-FluentLLM ★ PINNED ⑂
No description.
Python ★ 0 4mo agoExplain → -
RotateKV
Code used to reproduce the simulation results of RotateKV.
Python ★ 5 1y agoExplain → -
Awesome-Vision-Token-Pruning-for-VLMs
No description.
★ 4 1y agoExplain → -
Awesome-Diffusion-Quantization
No description.
★ 1 1y agoExplain → -
llm-compressor ⑂
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
★ 0 23h agoExplain → -
claude-code ⑂
An independent Python feature port of Claude Code, entirely rewritting from scratch using oh-my-codex. Educational Purpose only.
★ 0 3mo agoExplain → -
Claude-Code-2 ⑂
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands. All original source code is the property of Anthropic.
★ 0 3mo agoExplain → -
Awesome-Visual-Geometry-Grounded-Transformers
No description.
★ 0 5mo agoExplain → -
Awesome-VGGT
No description.
★ 0 5mo agoExplain → -
StreamVGGT ⑂
Code for Streaming 4D Visual Geometry Transformer
★ 0 10mo agoExplain → -
Awesome-Multimodal-KV-Compression
No description.
★ 0 1y agoExplain →
No repos match these filters.