Feeds to Scour
SubscribedAll
Scoured 27358 posts in 59.0 ms
OrionsLock/SALOMI: Research code for extreme low-bit transformer quantization and inference.  🔤Tokenization
github.com·21h·Hacker News·
TurboQuant: KV Cache Quantization to 3.5 Bits with Zero Accuracy Loss- ICLR 2026  🗜️Vector Compression
darshanfofadiya.com·4d·Hacker News·
Linear Regression from 1-bit Quantized Data  🔢Binary Embeddings
arxiv.org·1d·
Tq-KV – Rust implementation of TurboQuant that works on GGUF models  🎯Qdrant
news.ycombinator.com·1d·Hacker News·
Fused INT8 Weight-Only Quantization in Pallas  🔬RaBitQ
rishirajacharya.com·3d·
Fujitsu One Compression (LLM Quantization)  🎯Vector Quantization
fujitsuresearch.github.io·1d·Hacker News·
75% of What a Neural Network Learns is noise. So is 75% of What You Learned in School.  🔢BitNet
pub.towardsai.net·1d·
AdaLoRA-QAT: Adaptive Low-Rank and Quantization-Aware Segmentation  0Binary Vector Embeddings
arxiv.org·21h·
Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning  🏗️LLM Infrastructure
arxiv.org·21h·
SliderQuant: Accurate Post-Training Quantization for LLMs  🧠LLM Inference
arxiv.org·6d·
KV Cache Quantization for Self-Forcing Video Generation: A 33-Method Empirical Study  🔬RaBitQ
arxiv.org·2d·
Proxima: Near-storage Acceleration for Graph-based Approximate Nearest Neighbor Search in 3D NAND  💨Cache-Friendly Algorithms
arxiv.org·2d·
PQuantML: A Tool for End-to-End Hardware-aware Model Compression  🔬RaBitQ
arxiv.org·3d·
OneComp: One-Line Revolution for Generative AI Model Compression  📱Edge AI Optimization
arxiv.org·1d·
Once-for-All Channel Mixers (HYPERTINYPW): Generative Compression for TinyML  🔬RaBitQ
arxiv.org·6d·
Adaptive Block-Scaled Data Types  📏Linear Types
arxiv.org·2d·Hacker News·
Octree-based Learned Point Cloud Geometry Compression: A Lossy Perspective  🎯Vector Quantization
arxiv.org·2d·
Voxtral TTS  ✨Gemini
arxiv.org·6d·
RSR-core: A High-Performance Engine for Low-Bit Matrix-Vector Multiplication  ⚡Vectorized Execution
arxiv.org·2d·
ITQ3_S: High-Fidelity 3-bit LLM Inference via Interleaved Ternary Quantization with Rotation-Domain Smoothing  🧠LLM Inference
arxiv.org·2d·

Keyboard Shortcuts

Navigation
Next / previous item
j/k
Open post
oorEnter
Preview post
v
Post Actions
Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Recommendations
Add interest / feed
Enter
Not interested
x
Go to
Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help