Recent Posts

• SuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines
  by limoceon 3/4/2025, 7:26:48 AM with 0 comments
• SepLLM: Accelerate LLMs by Compressing One Segment into One Separator
  by limoceon 3/3/2025, 1:27:26 PM with 2 comments
• Step-Video-T2V: The Practice, Challenges, and Future of Video Foundation Model
  by limoceon 2/17/2025, 9:54:46 AM with 2 comments
• Logic R1: Reproduce DeepSeek R1 Zero on 2K Logic Puzzle Dataset
  by limoceon 2/5/2025, 4:02:04 AM with 0 comments
• Libnginx: Nginx as a Shared Library
  by limoceon 2/4/2025, 7:56:27 AM with 0 comments
• DeepSeek-VL2: Moe Vision-Language Models for Advanced Multimodal Understanding [pdf]
  by limoceon 12/13/2024, 12:53:00 PM with 0 comments
• Fast vectorizable algorithms of binary searching for floating point numbers
  by limoceon 11/15/2024, 12:53:13 AM with 0 comments
• New OpenAI Feature: Predicted Outputs
  by limoceon 11/5/2024, 2:47:19 AM with 7 comments
• Collaborative Filtering Is Wrong and Here Is Why
  by limoceon 10/24/2024, 9:03:26 AM with 0 comments
• REST: A Plug-and-Play Method for Accelerating LLM Without Additional Training
  by limoceon 10/20/2024, 6:13:57 AM with 0 comments
• Smoke 'em if you got 'em: Hacker gains root access using cigarette lighter
  by limoceon 10/12/2024, 1:20:01 PM with 0 comments
• O1 Replication Journey: A Strategic Progress Report
  by limoceon 10/9/2024, 8:09:57 AM with 0 comments
• Failures of Gradient-Based Deep Learning (2017) [pdf]
  by limoceon 8/15/2024, 10:19:24 AM with 0 comments
• Qwen2-VL
  by limoceon 8/14/2024, 8:20:03 AM with 0 comments
• Qwen2-Math
  by limoceon 8/8/2024, 3:00:18 PM with 12 comments
• FlexAttention: The Flexibility of PyTorch with the Performance of FlashAttention
  by limoceon 8/8/2024, 7:24:58 AM with 8 comments
• MiniCPM-v2.6: GPT-4V Level MLLM for Single/Multi Image and Video on Your Phone
  by limoceon 8/7/2024, 2:00:23 AM with 0 comments
• MindSearch: LLM-Based Web Search Engine Similar to Perplexity.ai and SearchGPT
  by limoceon 8/1/2024, 8:53:45 AM with 0 comments
• Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters
  by limoceon 6/12/2024, 11:01:55 AM with 0 comments
• PowerInfer-2: Fast Large Language Model Inference on a Smartphone
  by limoceon 6/11/2024, 2:19:20 PM with 0 comments
• Large-scale photonic chiplet Taichi empowers 160TOPS/W AI
  by limoceon 4/12/2024, 7:49:28 AM with 0 comments
• Asterinas: OS kernel written in Rust and providing Linux-compatible ABI
  by limoceon 3/5/2024, 8:52:13 AM with 0 comments
• Mq-deadline scalability improvements (with more than 100% improvement)
  by limoceon 1/20/2024, 12:04:54 PM with 0 comments
• Researchers Create First Functional Semiconductor Made from Graphene
  by limoceon 1/5/2024, 4:45:25 AM with 0 comments
• Wayland Enjoyed Many Successes in 2023
  by limoceon 1/2/2024, 3:54:56 AM with 0 comments
• Improving our safety with a physical quantities and units library
  by limoceon 12/23/2023, 6:01:29 AM with 18 comments
• Nesting chinstrap penguins sleep by seconds-long microsleeps
  by limoceon 12/22/2023, 2:31:54 PM with 0 comments
• PowerInfer: High-Speed Large Language Model Serving on Consumer-Grade GPUs
  by limoceon 12/19/2023, 12:19:09 PM with 1 comment
• Zpoline: System Call Hook for Linux
  by limoceon 7/20/2023, 4:18:15 AM with 0 comments
• Randomized Single-Source Shortest Path Algo. On Undirected Real-Weighted Graphs
  by limoceon 7/11/2023, 7:26:41 AM with 0 comments
• ChatGPT powered Rust proc macro that generates code at compile-time
  by limoceon 3/13/2023, 2:31:24 AM with 0 comments
• Memcpy is faster than memset on Intel i7 12700 with glibc 2.36
  by limoceon 1/1/2023, 12:50:49 PM with 1 comment
• Year-in-search-trends: Visualization of search interest over time
  by limoceon 12/30/2022, 1:28:50 PM with 0 comments
• Make call_rcu() lazy to save power
  by limoceon 12/30/2022, 12:58:41 PM with 0 comments
• IOMMUFD
  by limoceon 12/30/2022, 12:57:32 PM with 0 comments
• Chinese Chipmaker Loongson Readies 3A6000 to Tackle Zen 3 and Tiger Lake
  by limoceon 10/18/2022, 2:26:06 PM with 3 comments
• Skyplane: Optimizing Transfer Cost and Throughput Using Cloud-Aware Overlays
  by limoceon 10/18/2022, 9:39:33 AM with 1 comment
• Slirp Is Dead, Long Live Slirp: a New Approach to User-Mode Networking
  by limoceon 9/21/2022, 2:32:07 PM with 0 comments
• eRPC: A fast remote procedure call library for datacenters
  by limoceon 8/30/2022, 7:01:24 AM with 0 comments
• Poly-time algorithm for deciding Hilbert Nullstellensatz. A proof of P=NP
  by limoceon 8/16/2022, 3:03:44 PM with 12 comments
• How hard is it to open a file (2016)
  by limoceon 8/14/2022, 1:19:51 AM with 0 comments
• Kernel TLS 1.3 Rx improvements in Linux 5.20
  by limoceon 8/13/2022, 7:57:57 AM with 0 comments
• Resin: Holistic Service for Dealing with Memory Leaks in Production Cloud Infra
  by limoceon 8/8/2022, 8:30:00 AM with 0 comments
• YMTC launched 232-layer flash memory chip: performance improved by 50%
  by limoceon 8/3/2022, 3:21:31 PM with 0 comments
• Why JavaScript/Python are 8x/29x slower than C++, yet Java/Go can be Faster?
  by limoceon 7/27/2022, 2:51:15 PM with 0 comments