ViewTube

ViewTube
Sign inSign upSubscriptions
Filters

Upload date

Type

Duration

Sort by

Features

Reset

23,461 results

Bioinformatics Made Easy
How DNA Is Sequenced: From Sample to Digital Reads | Decoding Life (Ep. 03)

Every cell carries DNA — but how do scientists read the exact order of its bases? This episode follows the complete path from a ...

6:59
How DNA Is Sequenced: From Sample to Digital Reads | Decoding Life (Ep. 03)

38 views

4d ago

AI Agents Drawn
LLM Inference Explained: Prefill, Decode & Time to First Token

What happens between sending a prompt and seeing the answer? We draw LLM inference on one whiteboard: two phases, prefill ...

3:07
LLM Inference Explained: Prefill, Decode & Time to First Token

2 views

4d ago

Kai
I ran Qwen3.8 27B on $78 Card! (Better than expected)

I ran Qwen 3.8 27B on a $78 Nvidia Tesla P100, a 2016 data center card, and two of them hit 67 tokens per second with llama.cpp ...

33:52
I ran Qwen3.8 27B on $78 Card! (Better than expected)

61,680 views

1d ago

Dimitrii's Lab
You Can Decode Live Satellite Data From Your Balcony (RTL-SDR + L-Band)

Learn how to receive and decode live L-band AERO satellite transmissions—including Inmarsat ACARS text messages, ADS-C ...

15:15
You Can Decode Live Satellite Data From Your Balcony (RTL-SDR + L-Band)

1,513 views

5d ago

NetCam Pro
Decoding the 2-Tier Fabric_ Spine-Leaf Architecture.
7:57
Decoding the 2-Tier Fabric_ Spine-Leaf Architecture.

2 views

4d ago

AILinkDeepTech
Speculative Decoding: Rejection Sampling, Medusa, EAGLE-2 & Serving (Deep Dive)

Why do modern Large Language Models (LLaMA-3, DeepSeek-V3, GPT-4) run at less than one percent GPU compute utilization ...

16:03
Speculative Decoding: Rejection Sampling, Medusa, EAGLE-2 & Serving (Deep Dive)

67 views

4d ago

Core Concept Learning
NCP-GENL 14/34: Decoding Strategies and Ablation Studies | NVIDIA Generative AI LLMs Professional

Decoding Strategies and Ablation Studies explained for the NVIDIA Generative AI LLMs Professional exam: Decoding settings ...

3:47
NCP-GENL 14/34: Decoding Strategies and Ablation Studies | NVIDIA Generative AI LLMs Professional

11 views

5d ago

Cyber bro
CyberChef for Beginners 🔐 | Decode Base64, ROT13 & More! #cyberchef

What if I told you that strange-looking text could become readable in seconds? Meet CyberChef – The Cyber Swiss Army Knife!

3:49
CyberChef for Beginners 🔐 | Decode Base64, ROT13 & More! #cyberchef

23 views

7d ago

Trapture Explains
Change Data Capture (CDC) Explained: Debezium, Postgres WAL and MERGE

Copying your whole orders table every night is slow, misses deletes until the next run, and hammers production. Change data ...

9:42
Change Data Capture (CDC) Explained: Debezium, Postgres WAL and MERGE

18 views

6d ago

頭がよくなった気がするチャンネル
Tokenizer Encode and Decode: From Text to Token IDs and Back | Understand LLMs from Zero #12

How is a finished tokenizer vocabulary actually used? Encoding: split a new sentence into letters, apply the merge rules one at a ...

9:19
Tokenizer Encode and Decode: From Text to Token IDs and Back | Understand LLMs from Zero #12

9 views

1d ago

EMO Seminar
EMO Seminar || Yize Chen - Enhancing EV and PV Observability via Sparse Decoding

Yize Chen (University of Alberta) EMO Seminar · November 11, 2026 Abstract Rapid adoption of electric vehicles (EVs) and ...

1:00:57
EMO Seminar || Yize Chen - Enhancing EV and PV Observability via Sparse Decoding

63 views

6d ago

Paper Explained
2–3× Faster LLM Answers, Same Output | Speculative Decoding Explained

A small model drafts several tokens; the big model checks them all at once — and the output distribution is exactly the same.

16:19
2–3× Faster LLM Answers, Same Output | Speculative Decoding Explained

19 views

1d ago