bbzjk7's submissions | Hacker News

1.		Turbocharging LinkedIn's Recommendation Systems with SGLang (linkedin.com)
		1 point by bbzjk7 1 day ago \| past \| discuss
2.		IBM to Acquire Confluent (ibm.com)
		4 points by bbzjk7 3 days ago \| past \| discuss
3.		Three Levels of Running LLMs from Laptop to Cluster-Scale Distributed Inference (bentoml.com)
		3 points by bbzjk7 9 days ago \| past \| discuss
4.		OpenAI lost a court battle against the New York Times (businessinsider.com)
		10 points by bbzjk7 27 days ago \| past \| 1 comment
5.		Automating Benchmark Design (arxiv.org)
		1 point by bbzjk7 31 days ago \| past
6.		ChatGPT Usage Limits: What They Are and How to Get Rid of Them (bentoml.com)
		1 point by bbzjk7 48 days ago \| past
7.		Two federal judges say use of AI led to errors in US court rulings (channelnewsasia.com)
		8 points by bbzjk7 48 days ago \| past
8.		Refrag: Rethinking RAG Based Decoding (arxiv.org)
		2 points by bbzjk7 57 days ago \| past
9.		The Job Market Is Hell (aol.com)
		1 point by bbzjk7 78 days ago \| past
10.		Redis to Acquire Real-Time Data Platform Decodable (yahoo.com)
		1 point by bbzjk7 3 months ago \| past
11.		Nvidia Data Center GPUs Explained: From A100 to B200 and Beyond (bentoml.com)
		4 points by bbzjk7 3 months ago \| past
12.		A comprehensive list of 2025 tech layoffs (techcrunch.com)
		4 points by bbzjk7 3 months ago \| past
13.		Mirage 2 – Generative World Engine (twitter.com/dynamicslab_ai)
		1 point by bbzjk7 3 months ago \| past \| 1 comment
14.		Caote: KV Cache Eviction for LLMs (arxiv.org)
		3 points by bbzjk7 3 months ago \| past
15.		Benchmarks Show Speculative Decoding Needs the Right Draft Model for 3× Gains (bentoml.com)
		1 point by bbzjk7 4 months ago \| past
16.		Correlations: UI for debugging correlations of text and image embeddings (github.com/jina-ai)
		2 points by bbzjk7 6 months ago \| past
17.		[dupe] LLM-D: Kubernetes-Native Distributed Inference at Scale (github.com/llm-d)
		10 points by bbzjk7 6 months ago \| past \| 2 comments
18.		More NIH workers laid off, including cuts at the National Cancer Institute (fiercebiotech.com)
		23 points by bbzjk7 7 months ago \| past \| 1 comment
19.		Apple shuffles AI executive ranks in bid to turn around Siri (yahoo.com)
		336 points by bbzjk7 8 months ago \| past \| 562 comments
20.		You Have 7 Days to Act Following Gmail Lockout Hack Attacks, Google Says (forbes.com/sites/daveywinder)
		3 points by bbzjk7 8 months ago \| past
21.		The Complete Guide to DeepSeek Models: From V3 to R1 and Beyond (bentoml.com)
		2 points by bbzjk7 9 months ago \| past
22.		2024 State of AI Inference Infrastructure Survey Results (bentoml.com)
		2 points by bbzjk7 9 months ago \| past
23.		A Guide to ComfyUI Custom Nodes (bentoml.com)
		1 point by bbzjk7 11 months ago \| past
24.		Apache Iceberg Won the Open Table Wars (bigdatawire.com)
		1 point by bbzjk7 on Dec 5, 2024 \| past
25.		Aisuite: Unified interface to multiple GenAI providers (github.com/andrewyng)
		2 points by bbzjk7 on Nov 26, 2024 \| past
26.		Cloud Native Computing Foundation Announces Cert-Manager Graduation (cncf.io)
		2 points by bbzjk7 on Nov 14, 2024 \| past
27.		A List of Top Open-Source Embedding Models (bentoml.com)
		5 points by bbzjk7 on Oct 30, 2024 \| past \| 1 comment
28.		Prediction: AI Stock Will Outperform Nvidia over the Next Decade (fool.com)
		1 point by bbzjk7 on Oct 16, 2024 \| past \| 2 comments
29.		Top budget GPUs to buy under US$500 in 2024 (oneesports.gg)
		2 points by bbzjk7 on Oct 15, 2024 \| past \| 1 comment
30.		Vectorize debuts agentic RAG platform for real time enterprise data (venturebeat.com)
		1 point by bbzjk7 on Oct 9, 2024 \| past
		More