Feeds to Scour
SubscribedAll
Scoured 18233 posts in 874.2 ms
Hardware-Aware Reformulation of Convolutions for Efficient Execution on Specialized AI Hardware: A Case Study on NVIDIA Tensor Cores
arxiv.org·1d
Hardware Acceleration
Preview
Report Post
featurestorebook/mlfs-book: O'Reilly book - Building Machine Learning Systems with a feature store: batch, real-time, and LLMs
github.com·7h·
Discuss: Hacker News
🏗️LLM Infrastructure
Preview
Report Post
PRIMAL: Processing-In-Memory Based Low-Rank Adaptation for LLM Inference Accelerator
arxiv.org·1d
🧠LLM Inference
Preview
Report Post
Co-optimization Approaches For Reliable and Efficient AI Acceleration (Peking University et al.)
semiengineering.com·14h
Hardware Acceleration
Preview
Report Post
DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
machinelearning.apple.com·1d
🕯️Candle ML
Preview
Report Post
ANN v3: 200ms p99 query latency over 100 billion vectors
turbopuffer.com·1d·
Discuss: Hacker News
🔮Prefetching
Preview
Report Post
Qdrant - Vector Database
qdrant.tech·1d
🎯Qdrant
Preview
Report Post
Why AI Needs GPUs and TPUs: The Hardware Behind LLMs
blog.bytebytego.com·2d
Hardware Acceleration
Preview
Report Post
Youtube Channel Transcript Embeddings
shruggingface.com·1d
🕸️Sparse Vectors
Preview
Report Post
Hippocampus model implementing a Turing machine
pub.towardsai.net·4h
🧠LLM Inference
Preview
Report Post
Uncovering Unfaithful CoT in Deceptive Models
lesswrong.com·6h
🛡️AI Security
Preview
Report Post
Everything Moe
ianbarber.blog·1d·
Discuss: Hacker News
🔤Tokenization
Preview
Report Post
Implementing Dino from Scratch
logits.bearblog.dev·1d·
Discuss: Hacker News
🎯Qdrant
Preview
Report Post
ClickPy at 2 Trillion rows: Scaling ingestion and fixing the past
clickhouse.com·21h
ClickHouse
Preview
Report Post
AI Systems Performance Engineering
github.com·7h·
Discuss: Hacker News
📅Resource Scheduling
Preview
Report Post
Meet Z.AI 4.7 Flash, a Low-Cost Local AI Model for Coding & Smart Tasks
geeky-gadgets.com·18h
🏗️LLM Infrastructure
Preview
Report Post
Show HN: 4x faster Deep Learning training – we replaced the DataLoader with Rust
news.ycombinator.com·1d·
Discuss: Hacker News
🔥Burn
Preview
Report Post
Streamlining CUB with a Single-Call API
developer.nvidia.com·10h
🏟️Arena Allocators
Preview
Report Post
CUDA Programming: From Zero to GPU Kernels
pythongiant.github.io·21h·
Discuss: Hacker News
Hardware Acceleration
Preview
Report Post
AI Policy NotebookLM
mguhlin.org·20h
👨‍💻AI Coding
Preview
Report Post

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