Search: github.com/r00m | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

61.

Show HN: Self-hosted virtual events starter kit built on Vercel and 100ms

github.com/vercel

4 years ago

4 points

62.

Azure CLI takes ~700MB of disk space

github.com/Azure

3 years ago

3 points

63.

Add 500M tokens of context space to any LLM with <300ms latency

3 months ago

3 points

64.

OSS voice AI stack – <500ms latency, <5¢/min, interruption, ack, guardrails

github.com/bolna-ai

2 years ago

3 points

65.

Can Conductor handle 100M workflows per day?

github.com/Netflix

4 years ago

3 points

66.

Show HN: GoldenMatch – 100M-row dedupe on Ray in 213s, no Spark, Arrow-native

github.com/benseverndev-oss

18 days ago

3 points

67.

From 800ms to ~25ms: harness-driven optimization of a CUDA matmul kernel

github.com/YupengHan

2 months ago

3 points

68.

Show HN: Voice skill for AI agents – sub-200ms latency via native SIP

github.com/nia-agent-cyber

4 months ago

3 points

69.

Show HN: I replaced a 200MB JVM process with a 52KB binary that speaks Kafka

github.com/awneesht

4 months ago

3 points

70.

Show HN: The equation for smoke vortices also describes 100M° fusion plasma

github.com/Lulzx

6 months ago

3 points

71.

Hdslb: Open-source 100M+ concurrent session L4 load balancer

github.com/intel

3 years ago

3 points

72.

Show HN: Skales – Local AI agent desktop app (.exe/.dmg, 300MB idle RAM)

4 months ago

2 points

73.

FMLLM: 4mb training data, 100mb model, Fibonacci embeddings, near-coherent. WTF?

github.com/henrygabriels

10 months ago

gabriel666smith

2 points

74.

Show HN: I built a <400ms latency voice agent that runs on a 4gb vram GTX 1650"

github.com/pheonix-delta

4 months ago

2 points

75.

Orthanc – Open-Source Memory Layer for Agents (Sub-200ms Latency)

github.com/orthanc-protocol

5 months ago

2 points

76.

logicanalyzer: 24-120 channel, 400Msps Pico 2-based logic analyzer

github.com/gusmanb

a year ago

2 points

77.

Show HN: Vectorchord – Host 100M+ 768D Vectors for $250/m, pgvector-compatible

github.com/tensorchord

a year ago

2 points

78.

LoLRa Transmit 900MHz LoRa frames surprisingly far without a radio

github.com/cnlohr

2 years ago

2 points

79.

E-commerce app Pinduoduo used Android 0-days to turn 100M+ phones into a botnet [pdf]

github.com/davincifans101

3 years ago

2 points

80.

We checkpoint Chrome to NVMe and restore it in 500ms ()

3 months ago

2 points

81.

Helsinki professor Jörg Tiedemann – 500M translations in 188 languages

github.com/Helsinki-NLP

5 years ago

2 points

82.

500M+ Dump of Kinect Sensor Data

github.com/adafruit

16 years ago

2 points

83.

100M commits to GitHub without using Git push

github.com/Wuerfelhusten

2 months ago

1 points

84.

Bounded O(1) Coordinator Benchmark (100M cycles JSON included)

github.com/SeasonedAsh

6 months ago

1 points

85.

COYO-700M: Large-Scale Image-Text Pair Dataset

github.com/kakaobrain

4 years ago

1 points

86.

Show HN: Sketchlog – 100M events compressed to 93 KB using streaming sketches

10 days ago

1 points

87.

Show HN: A CLI that fact-checks text using a 500MB local model and web search

github.com/kouhxp

12 days ago

1 points

88.

Porting a Scratch-Built 500M LLM Training Pipeline to ROCm on Strix Halo

github.com/epscylonb

2 months ago

thomasfromcdnjs

1 points

89.

Memory Leaks as a Service: Allocate 100MiB every hour, without freeing it

github.com/morgangallant

3 years ago

1 points

90.

Telegram: 500m Active Users and a Noble Growth Plan

gist.github.com

5 years ago

1 points