Tech

Humming: Fast, Flexible Kernels for Quantized Inference

Hacker News (Newest) By gmays Oct 22, 2026 · 8:42 PM 3 views 0 comments

Humming: Fast, Flexible Kernels for Quantized Inference — Image: Hacker News (Newest)

Article URL: https://vllm.ai/blog/2026-10-21-humming

Comments URL: https://news.ycombinator.com/item?id=50203547

Points: 1

# Comments: 0

Hacker News (Newest) Original story · vllm.ai

Read the full story

How does this story make you feel?

👍 ❤️ 💡 😮 😂 😢 😠

Discussion (0)

No comments yet. Start the conversation!

Hacker News (Newest) + Follow

Section: Tech + Follow

Up next from Hacker News (Newest)

Red-Teaming OpenAI's Internal Agent Monitoring Systems

Article URL: https://blog.redwoodresearch.org/p/red-teaming-openais-internal-agent Comments URL: https://news.ycombinator.com/item?id=50203538 Points: 1 # Comments: 0

Hacker News (Newest) Oct 22, 2026

Show HN: Golang DL/ML primitives with inference, diffusion, vision, systemone

Hacker News (Newest) Oct 14, 2026

Tech

Architect Launches Liquid Inference, a Real-Time Auction for LLM Inference

MarkTechPost Oct 8, 2026

Tech

NVIDIA Nsight Python Tutorial: How to Profile GPU Kernels

MarkTechPost Oct 21, 2026

Discussion (0)

More to read

Ubuntu firmware HWE will prevent issues on older kernel

DeepSeek Open-Sources DeepInfer, the Inference Framework Behind DeepSeek-V4.1-Flash

What inference engine and KV offload engine do you use and why?