HackerTrans
TopNewTrendsCommentsPastAskShowJobs

zagwdt

no profile record

Submissions

Inference Optimization for MiniMax Sparse Attention

together.ai
1 points·by zagwdt·bulan lalu·0 comments

DeepSeek V4 in vLLM: Efficient Long-Context Attention

vllm-website-pdzeaspbm-inferact-inc.vercel.app
3 points·by zagwdt·3 bulan yang lalu·0 comments

Introspective Diffusion Language Models

introspective-diffusion.github.io
281 points·by zagwdt·3 bulan yang lalu·55 comments

EinsteinArena: Harnessing the collective intelligence of agents in the wild

einsteinarena.com
5 points·by zagwdt·3 bulan yang lalu·0 comments

RL Meets Adaptive Speculative Training

together.ai
2 points·by zagwdt·3 bulan yang lalu·0 comments

Weak models excel at long context tasks

together.ai
2 points·by zagwdt·4 bulan yang lalu·0 comments

TorchSpec: Speculative Decoding Training at Scale

pytorch.org
2 points·by zagwdt·4 bulan yang lalu·0 comments

[untitled]

1 points·by zagwdt·4 bulan yang lalu·0 comments

Flash Attention 4

together.ai
1 points·by zagwdt·4 bulan yang lalu·0 comments

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

together.ai
1 points·by zagwdt·5 bulan yang lalu·0 comments

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

notion.com
2 points·by zagwdt·5 bulan yang lalu·0 comments

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

together.ai
219 points·by zagwdt·5 bulan yang lalu·96 comments

comments

zagwdt
·3 bulan yang lalu·discuss
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