Feeds to Scour
SubscribedAll
Scoured 199872 posts in 23.1 ms
Article: Time-Series Storage: Design Choices That Shape Cost and Performance  📊Columnar Storage
infoq.com·2d
Hardware Memory Compression Is the Solution to the Memory Wall  ⚡Compression Hardware
eetimes.com·3d
2.3x KV Cache Compression at 32k Context  🏠Local LLM Deployment
github.com·9h·Hacker News
GRC: Unifying Reasoning-Driven Generation, Retrieval and Compression  🤖LLM
arxiv.org·2d
Adola: Reducing LLM input tokens by 70%  🤖LLM
adola.app·5d·Hacker News, Hacker News
AMD DGF: An Open Geometry Compression Standard  🎮GPU Microarchitecture
gpuopen.com·1d·Hacker News
sipsalabs/ultracompress: Extreme compression infrastructure for large language models. pip install ultracompress  🌊Streaming Compression
github.com·6d·Hacker News
High-arity Sample Compression  🌊Streaming Compression
arxiv.org·2d
FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression  ⚡Compression Hardware
arxiv.org·2d
When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression  🎯Data Locality
arxiv.org·3d
KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving  🌊Streaming Compression
arxiv.org·1d
From Compression to Accountability: Harmless Copyright Protection for Dataset Distillation  🧪Archive Fuzzing
arxiv.org·1d
OpenZL: Using Graphs to Compress Smaller and Faster  🌊Streaming Compression
arxiv.org·3d
MedCore: Boundary-Preserving Medical Core Pruning for MedSAM  ⚡LLM Optimization
arxiv.org·1d
Transforming the Use of Earth Observation Data: Exascale Training of a Generative Compression Model with Historical Priors for up to 10,000x Data Reduction  ⚡High Performance Computing
arxiv.org·3d·Hacker News
Qwen-Image-VAE-2.0 Technical Report  🎨AI Image Gen
arxiv.org·1d
NCCLZ: Compression-Enabled GPU Collectives with Decoupled Quantization and Entropy Coding  ⚡High Performance Computing
arxiv.org·2d
LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction  ⚡LLM Optimization
arxiv.org·4d
Different Prompts, Different Ranks: Prompt-aware Dynamic Rank Selection for SVD-based LLM Compression  ⚡LLM Optimization
arxiv.org·3d
Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control  🏗️LLM Infrastructure
arxiv.org·4d

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
Save / unsave
s

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