How to Quadruple LLM Decoding Performance with Speculative Decoding (SpD) and Microscaling (MX) Formats on Qualcomm® Cloud AI 100
How to Quadruple LLM Decoding Performance with Speculative Decoding (SpD) and Microscaling (MX) Formats on Qualcomm® Cloud AI 100
Aug 1, 2024
qualcomm.com
Faster LLMs: Accelerate Inference with Speculative Decoding
Faster LLMs: Accelerate Inference with Speculative Decoding
10 months ago
ibm.com
Transformer Explainer: LLM Transformer Model Visually Explained
Transformer Explainer: LLM Transformer Model Visually Explained
Jun 22, 2024
github.io
Transformer decoders explained step-by-step from scratch
41:28
Transformer decoders explained step-by-step from scratch
3 months ago
MSNLearn With Jay
Building Local AI: Getting Started with vLLM
13:09
Building Local AI: Getting Started with vLLM
74 views1 month ago
YouTubeProbably Private
AI Explained: Speculative decoding with vLLM
2:42
AI Explained: Speculative decoding with vLLM
1K views3 weeks ago
YouTubeRed Hat
LK Losses: Optimizing Speculative Decoding
4:18
LK Losses: Optimizing Speculative Decoding
1 month ago
YouTubeAI Research Roundup
GigaWorld-Policy: An Efficient Action-Centered World--Action Model (Mar 2026)
17:46
GigaWorld-Policy: An Efficient Action-Centered World--Action Model (Mar 2026)
17 views1 week ago
YouTubeAI Paper Slop
Speculative Speculative Decoding for Faster LLM Inference
1:23
Speculative Speculative Decoding for Faster LLM Inference
1.3K views3 weeks ago
YouTubeRajistics - data science, AI, and machine learning
NVIDIA's VP of AI Explains Why They Give Away Their Best Models | Kari Briski × Kim Isenberg
21:17
NVIDIA's VP of AI Explains Why They Give Away Their Best Models | Kari Briski × Kim Isenberg
1.2K views1 week ago
YouTubeSuperintelligence
ggml and llama.cpp join Hugging Face & Custom AI chips for fast inference - Hacker News (Feb 20, ...
20:35
ggml and llama.cpp join Hugging Face & Custom AI chips for fast inference - Hacker News (Feb 20, ...
1 month ago
YouTubeThe Automated Daily
GBV: The AI Speed Hack You Need Now (30% Faster Inference) #Shorts
0:58
GBV: The AI Speed Hack You Need Now (30% Faster Inference) #Shorts
1 month ago
YouTubeCollapsedLatents
In-model computation gets real & Cloud inference shifts beyond GPUs - AI News (Mar 17, 2026)
8:45
In-model computation gets real & Cloud inference shifts beyond GPUs - AI News (Mar 17, 2026)
21 views2 weeks ago
YouTubeThe Automated Daily
【論文解説】【爆速化】推測デコーディングをスパース計算で検証！驚きの成果公開！
14:13
【論文解説】【爆速化】推測デコーディングをスパース計算で検証！驚きの成果公開！
12 views1 month ago
YouTube論文解説チャンネル
What is Speculative decoding - Speculative decoding Explained #generativeai #RAG #ai #llm
1:05
What is Speculative decoding - Speculative decoding Explained #generativeai #RAG #ai #llm
273 views3 weeks ago
YouTubeMed Bou | AI Tutorials
Step 3.5 Flash: Fast 11B MoE for Agentic Tasks
4:57
Step 3.5 Flash: Fast 11B MoE for Agentic Tasks
63 views1 month ago
YouTubeAI Research Roundup
EP5: Speculative Decoding with Nadav Timor
1:02:23
EP5: Speculative Decoding with Nadav Timor
116 views6 months ago
YouTubeThe Information Bottleneck
Encoder Decoder Network - Computerphile
6:20
Encoder Decoder Network - Computerphile
156.6K viewsJun 13, 2018
YouTubeComputerphile
The Hilbert transform
9:46
The Hilbert transform
159.2K viewsOct 1, 2017
YouTubeMike X Cohen
Transformer models: Encoder-Decoders
6:47
Transformer models: Encoder-Decoders
105.6K viewsJun 14, 2021
YouTubeHugging Face
The Narrated Transformer Language Model
29:30
The Narrated Transformer Language Model
346.3K viewsOct 26, 2020
YouTubeJay Alammar
Problems With Encoders And Decoders- Indepth Intuition
11:09
Problems With Encoders And Decoders- Indepth Intuition
44.1K viewsAug 5, 2020
YouTubeKrish Naik
Speculative Decoding Explained
37:34
Speculative Decoding Explained
7.8K viewsDec 21, 2023
YouTubeTrelis Research
Vision Transformer Attention
9:37
Vision Transformer Attention
14.2K viewsOct 21, 2021
YouTubeEscVM
Vision Transformers explained
13:44
Vision Transformers explained
69.5K viewsJul 1, 2023
YouTubeCode With Aarohi
LLM Jargons Explained: Part 4 - KV Cache
13:47
LLM Jargons Explained: Part 4 - KV Cache
10.8K viewsMar 24, 2024
YouTubeSachin Kalsi
Why Isn't ChatGPT Slow? (System Design)
0:51
Why Isn't ChatGPT Slow? (System Design)
1.2K views3 months ago
YouTubeTech with infographics
Transformer models: Decoders
4:27
Transformer models: Decoders
78.3K viewsJun 14, 2021
YouTubeHugging Face
Set Block Decoding: Faster LLM Inference
2:55
Set Block Decoding: Faster LLM Inference
53 views6 months ago
YouTubeAI Research Roundup
Deep Dive: Optimizing LLM inference
36:12
Deep Dive: Optimizing LLM inference
47K viewsMar 11, 2024
YouTubeJulien Simon
See more