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 Dec…
Aug 1, 2024
qualcomm.com
Speculative Decoding — Think Fast⚡, Then Think Right✅
Speculative Decoding — Think Fast⚡, Then Think Right✅
1K views9 months ago
substack.com
Faster LLMs: Accelerate Inference with Speculative Decoding
Faster LLMs: Accelerate Inference with Speculative Decoding
7 months ago
ibm.com
【GOSIM HANGZHOU 2025】Yikai Zhu, Lukec Wang：SpecForge - Speculative Decoding Model Training Framework
17:51
【GOSIM HANGZHOU 2025】Yikai Zhu, Lukec Wang：SpecForge - S…
1 views1 month ago
YouTubeGOSIM Foundation
NVIDIA made AI 6x faster overnight || Xtudio
1:20
NVIDIA made AI 6x faster overnight || Xtudio
2.8K views1 month ago
YouTubePushpendra Chauhan
Llama-3.1 & Qwen3 Now 4x Faster
0:24
Llama-3.1 & Qwen3 Now 4x Faster
89 views2 weeks ago
YouTubeGradient Update
Generate 10 Tokens At Once - Faster LLM INFERENCE - AdaSPEC - Speculative Decoding Improvement
11:34
Generate 10 Tokens At Once - Faster LLM INFERENCE - AdaSPE…
376 views2 months ago
YouTubeVuk Rosić
13:55
LLM Inference 3x Faster, Speculative Decoding Completely …
171 views2 months ago
YouTube딥러닝논문읽기모임
1:41
How to speed up AI without new hardware
874 views2 months ago
YouTubeRed Hat
6:53
How Speculative Decoding Makes LLMs 2.5x Faster (The Secret to F…
4 views3 months ago
YouTubeFranksWorld of AI
17:56
Behind the Stack, Ep 11 - Speculative Decoding
1 views2 months ago
YouTubeDoubleword
0:51
Why Isn't ChatGPT Slow? (System Design)
1.2K views2 weeks ago
YouTubeLogicLayers
1:02:23
EP5: Speculative Decoding with Nadav Timor
3 months ago
YouTubeThe Information Bottleneck
0:31
The Hardware That Enables "Cloud Quality" AI on a Local Machine
1.8K views4 months ago
YouTubeSuper Data Science: ML & AI Podcast with Jon …
12:51
Frontier AI Research: The New L5 Standard for 2026?
55 views1 week ago
YouTubeLogicLayers
0:36
How AI Replies So Fast! ⚡ Speculative Decoding
130 views2 weeks ago
YouTubeMr. Doubty – Short. Smart. Techy
0:06
Vivek Alamuri on Instagram: "Forget about bigger GPUs, you can do a …
8.8K views1 month ago
Instagramvivek.engineer
1:04:45
[EP24] 硅谷线下AI infra, vLLM Speculative Decoding
2.7K views3 months ago
bilibili月球大叔
Speculative Decoding and Efficient LLM Inference with Chris Lott - 717
1.4K views11 months ago
YouTubeThe TWIML AI Podcast with Sam Charrington
What is Speculative Sampling? | Boosting LLM inference speed
3.3K viewsNov 20, 2024
YouTubeAssemblyAI
Implementation and optimization of MTP for DeepSeek R1 in TensorR…
1.3K views6 months ago
YouTubeNVIDIA Developer
6:47
Transformer models: Encoder-Decoders
96.8K viewsJun 14, 2021
YouTubeHuggingFace
5:37
🔵 Speculate Speculative Speculator Speculation - Speculate Meaning …
5.7K viewsFeb 10, 2021
YouTubeiswearenglish
11:19
(50) Lockpicking: Bypassing and Decoding Masterlock Combinatio…
109.2K viewsSep 14, 2017
YouTubeMM Developer
1:39
Rajiv Shah on Instagram: "Sweep AI showed how to really make autoc…
5.9K views3 months ago
Instagramrajistics
39:01
EZ撸paper: DeepSeek-V3 论文中的隐藏细节 (part 4)：从入门到精通Dee…
12.8K views11 months ago
YouTubeEZ.Encoder Academy
2:28:30
Deploying Fine-Tuned Models
2.8K viewsJul 22, 2024
YouTubeHamel Husain
13:47
LLM Jargons Explained: Part 4 - KV Cache
10.3K viewsMar 24, 2024
YouTubeSachin Kalsi
0:49
#luckygameplay
94.1K views2 weeks ago
YouTubeLLM ARAFAT YT
2:55
Set Block Decoding: Faster LLM Inference
35 views4 months ago
YouTubeAI Research Roundup
See more videos
Static thumbnail place holder