HNHacker News
TopNewBestAskShowJobs

immortal3

198 karma · joined April 11, 2020

submissionscomments

Improving LLM Inference with Continuous Batching: Orca Through Tinyorca

junupark.xyz·2 pts·immortal3·
0

Bits-per-Byte (BPB): a tokenizer-agnostic way to measure LLMs

dipkumar.dev·1 pts·immortal3·
0

Creativity Is a Luxury

dipkumar.dev·2 pts·immortal3·
0

GPT-5 Router – Inevitable Future of Chat Interfaces

dipkumar.dev·3 pts·immortal3·
0

Instruction Aware Embeddings – Why Your Retriever Is Failing

dipkumar.dev·1 pts·immortal3·
0

Improving Retrieval in RAG (Via Recall, Precision, and NDCG)

dipkumar.dev·2 pts·immortal3·
0

Show HN:AceVocab - Learn and master the vocabulary featured in the GRE/GMAT

acevocab.com·3 pts·immortal3·
0

AWS BedRock – Converse API – A single endpoint for all models?

dipkumar.dev·2 pts·immortal3·
0

Essential Database Design: Five Fields Every Table Must Have

dipkumar.dev·3 pts·immortal3·
1

India issues notice to Google for blocking count over nude childhood photo

deccanherald.com·3 pts·immortal3·
0

Hugging Face raises $235M from investors including Salesforce and Nvidia

techcrunch.com·378 pts·immortal3·
203

Speeding up the GPT with KV cache (memoization)

immortal3.github.io·2 pts·immortal3·
0