Speculative Decoding — Think Fast⚡, Then Think Right✅
Speculative Decoding — Think Fast⚡, Then Think Right✅
Apr 13, 2025
substack.com
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
Faster LLMs: Accelerate Inference with Speculative Decoding
Faster LLMs: Accelerate Inference with Speculative Decoding
11 months ago
ibm.com
Multi-Token Prediction (MTP): Accelerating Local Models with no Quality Loss
17:15
Multi-Token Prediction (MTP): Accelerating Local Models with n…
1.4K views1 week ago
YouTubeOnchain AI Garage
Speculative Decoding: Make AI 2-3x Faster for Free | Tech Decoded
6:13
Speculative Decoding: Make AI 2-3x Faster for Free | Tech Decoded
3 views1 month ago
YouTubeToc am
Multi-Token Prediction: Why Your GPU Runs LLMs 3x Faster
8:37
Multi-Token Prediction: Why Your GPU Runs LLMs 3x Faster
4 views2 weeks ago
YouTubeDevsplainers
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding
9:11
Accelerating RL Post-Training Rollouts via System-Integrated Sp…
8 views1 week ago
YouTubeCosmoX
3:08
What is Speculative Decoding ?
38 views2 weeks ago
YouTubeDeepManim
7:09
Don't use speculative decoding until you watch this
7 views1 month ago
YouTubeDigitalOcean
12:09
【深堀り】Gemma 4 MTP ドラフター公開 — 投機的デコーディング …
59 views1 week ago
YouTubeずんだもんのテックニュース3分
8:44
MTP Just Hit Llama.cpp — And It Doubles Speed (For Chinese Mod…
2 weeks ago
YouTubeDigital Dreamscapes
1:31
ContextForge — AMD AI Hackathon 2026
2 weeks ago
YouTubePablo Manuel Suarez
40:19
Speculation is all you need: Intro to Speculative Decoding for High Per…
1 views2 months ago
YouTubeModal
21:28
The Physics of LLM Inference at Scale | Suman Debnath (Anyscale…
29 views1 week ago
YouTubeOnehouseHQ
8:27
600 Toks/Second Gemma4-26B —The Setting That Actually Wins (…
3.4K views2 weeks ago
YouTubeTech-Practice
5:04
Speculative Decoding: 2-3x Faster LLMs for Free
1 views1 month ago
YouTubeThe AI Century
23:40
Speculative Speculative Decoding: How to Parallelize Drafting and ... f…
178 views2 months ago
YouTubeXiaol.x
0:36
The regex trick that beats structured output #ai #coding #performance
1.3K views1 month ago
YouTubeJimi V. (Bitswired)
0:38
3.5K+ Stars • AI/ML | DFlash — Faster LLM Inference via Block Dif…
1.1K views2 weeks ago
YouTubeneural-nexus
0:31
Speculative Decoding • LLM Acceleration Patterns
1 views1 month ago
YouTubeTechnical Interview Essentials A–Z
9:32
Qwen3.6-27B NVFP4+MTP vLLM Benchmark TG 190tok/s — RTX P…
303 views2 weeks ago
YouTubeksh3
1:27
Stop Serving Open-Source LLMs the Slow Way - #aideveloperhub #vll…
44 views1 week ago
YouTubeAI Developer Hub
12:45
Speculative Decoding & Inference Speed — 2-3x Faster LLMs With Z…
2 weeks ago
YouTubeJeff Heidelberger
5:07
Cyber-Rus: Breaking Speed Limits with Qwen 3-8B and DFlash
1 week ago
YouTubeYAinvestAI
2:35
别盲跟！SPEED-Bench 实测 Speculative Decoding 在 vLLM 值 …
4 views2 months ago
YouTubeAI 决策内参
4:56
NeMo RL：Speculative Decoding 把 8B rollout 提速到 1.8×，235B 估计 …
5 views3 weeks ago
YouTube智用
2:08
How ChatGPT Serves 100M Users in Real Time ⚡ (LLM Inference, Explai…
4 views2 weeks ago
YouTubePriya Bansal
3:54
2026-04-30｜後端工程師的 AI 推論工程選型：從 batching 到 workloa…
2 weeks ago
YouTubeTodayShip
0:26
Researchers found a way to make LLMs 8.5x faster!(without compro…
155.1K views2 weeks ago
x.comAvi Chawla
1:52
🚀 Gemma4 MTP (Multi-Token Prediction) is Google's implement…
194 views1 week ago
x.comAbdel SGHIOUAR
See more videos
Static thumbnail place holder