HNGlance

TopBestNewShow

HN user

zagwdt

184 karma
Posts11
Comments1
View on HN
www.together.ai 1mo ago
TO

Inference Optimization for MiniMax Sparse Attention

zagwdt
1pts0
vllm-website-pdzeaspbm-inferact-inc.vercel.app 2mo ago
VL

DeepSeek V4 in vLLM: Efficient Long-Context Attention

zagwdt
3pts0
introspective-diffusion.github.io 3mo ago
IN

Introspective Diffusion Language Models

zagwdt
281pts55
einsteinarena.com 3mo ago
EI

EinsteinArena: Harnessing the collective intelligence of agents in the wild

zagwdt
5pts0
www.together.ai 3mo ago
TO

RL Meets Adaptive Speculative Training

zagwdt
2pts0
www.together.ai 3mo ago
TO

Weak models excel at long context tasks

zagwdt
2pts0
pytorch.org 4mo ago
PY

TorchSpec: Speculative Decoding Training at Scale

zagwdt
2pts0
www.together.ai 4mo ago
TO

Flash Attention 4

zagwdt
1pts0
www.together.ai 4mo ago
TO

CoderForge-Preview: SOTA open dataset for training efficient coding agents

zagwdt
1pts0
www.notion.com 5mo ago
NO

Two years of vector search at Notion: 10x scale, 1/10th cost

zagwdt
2pts0
www.together.ai 5mo ago
TO

Consistency diffusion language models: Up to 14x faster, no quality loss

zagwdt
219pts96
An update on recent Claude Code quality reports 3 months ago

ngl lost alot of trust in cc after reading this, specially point 1

how do you just do that to millions of users building prod code with your shit

0ThreadHN

HNGlance

© 2024-2026 HN Glance. Story content belongs to its original sources.

  • Privacy
  • Terms