GPU Course 06: vLLM TP vs EP Explained: How to achieve high throughput / low latency (InferenceX)
35:52
YouTubeFaradawn Yang
GPU Course 06: vLLM TP vs EP Explained: How to achieve high throughput / low latency (InferenceX)
In this lecture, we break down vLLM tensor parallelism vs expert parallelism for real enterprise LLM inference. We start from production constraints like SLA, TTFT, TPOT, tokens per second, throughput, latency, and cost per million tokens, then explain how to choose TP, DP, and EP for dense models, MoE models, and DeepSeek-style inference ...
310 views3 weeks ago
TensorFlow Tutorial
TensorFlow Tutorial: From Tensors to Training
13:11
TensorFlow Tutorial: From Tensors to Training
YouTubeSocratica
4.1K views3 weeks ago
TensorFlow Full Course 2025 | TensorFlow Tutorial for Beginners | TensorFlow Course| Simplilearn
5:47:58
TensorFlow Full Course 2025 | TensorFlow Tutorial for Beginners | TensorFlow Course| Simplilearn
YouTubeSimplilearn
8.8K views8 months ago
TensorFlow Crash Course for Beginners (2026) | Daniel Bourke
22:56:49
TensorFlow Crash Course for Beginners (2026) | Daniel Bourke
YouTubeZero To Mastery
80.5K views10 months ago
Top videos
Scale ANY Model: PyTorch DDP, ZeRO, Pipeline & Tensor Parallelism Made Simple (2025 Guide)
30:05
Scale ANY Model: PyTorch DDP, ZeRO, Pipeline & Tensor Parallelism Made Simple (2025 Guide)
YouTubeZachary Mueller
1.5K views11 months ago
Lecture 3: Tensor and Sequence Parallelism
1:01:43
Lecture 3: Tensor and Sequence Parallelism
YouTubeAstarag Mohapatra
175 views4 months ago
The challenge of managing parallelism and data-movement for tensor computations on GPUs
1:04:05
The challenge of managing parallelism and data-movement for tensor computations on GPUs
YouTubeSimons Institute for the
125 views8 months ago
PyTorch Basics
AI Engineering Full Course (PyTorch) 2026 UPDATED | Beginner to Advanced | One Shot | Sagar Chouksey
4:49:58
AI Engineering Full Course (PyTorch) 2026 UPDATED | Beginner to Advanced | One Shot | Sagar Chouksey
YouTubeCoding With Sagar
103.8K views6 months ago
PyTorch Tensors: The Data Structure Behind Deep Learning
12:17
PyTorch Tensors: The Data Structure Behind Deep Learning
YouTubeSocratica
9.1K views4 weeks ago
Lec 06 | Introduction to PyTorch
1:02:58
Lec 06 | Introduction to PyTorch
YouTubeNPTEL IIT Delhi
17.5K viewsJan 31, 2025
Scale ANY Model: PyTorch DDP, ZeRO, Pipeline & Tensor Parallelism Made Simple (2025 Guide)
30:05
Scale ANY Model: PyTorch DDP, ZeRO, Pipeline & Tensor Parallelism Made Simple (2025 Guide)
1.5K views11 months ago
YouTubeZachary Mueller
Lecture 3: Tensor and Sequence Parallelism
1:01:43
Lecture 3: Tensor and Sequence Parallelism
175 views4 months ago
YouTubeAstarag Mohapatra
The challenge of managing parallelism and data-movement for tensor computations on GPUs
1:04:05
The challenge of managing parallelism and data-movement for tensor computations on GPUs
125 views8 months ago
YouTubeSimons Institute for the Theory of Computing
LLM Inference Optimization #2: Tensor, Data & Expert Parallelism (TP, DP, EP, MoE)
20:18
LLM Inference Optimization #2: Tensor, Data & Expert Parallelism (TP, DP, EP, MoE)
4.6K views8 months ago
YouTubeFaradawn Yang
Let's Build Pipeline Parallelism from Scratch – Tutorial
3:22:24
Let's Build Pipeline Parallelism from Scratch – Tutorial
37.3K views5 months ago
YouTubefreeCodeCamp.org
Computational model and algorithms for tensor core units
35:21
Computational model and algorithms for tensor core units
111 views8 months ago
YouTubeSimons Institute for the Theory of Computing
Ep 60: Data vs Model Parallelism — Two Ways to Scale | LLM Mastery Podcast
21:09
Ep 60: Data vs Model Parallelism — Two Ways to Scale | LLM Mastery Podcast
9 views3 months ago
YouTubecarlos Hernandez
1:07:07
Lecture 87: Low Latency Communication Kernels with NVSHMEM
1.3K views6 months ago
YouTubeGPU MODE
34:08
[Picotron tutorial] Part 2: Tensor Parallel
2.8K viewsJan 7, 2025
YouTubeFerdinand Mom
1:07:38
ML Performance Reading Group Session 11: Async Tensor Parallelism
813 viewsMay 18, 2025
YouTubeEleutherAI
49:19
Trelis Research LIVE: vLLM v0 vs v1. Data vs Tensor Parallel Inference & Fine-tuning.
719 views10 months ago
YouTubeTrelis Research
36:46
Unstructured Sparsity Meets Tensor Cores: Lessons from Sparse Attention and MoE
221 views8 months ago
YouTubeSimons Institute for the Theory of Computing
1:07:08
Lecture 87: Low Latency Communication Kernels with NVSHMEM
952 views6 months ago
YouTubeGPU MODE
3:03:48
Lecture 48: The Ultra Scale Playbook
10.5K viewsMar 2, 2025
YouTubeGPU MODE
28:31
The Engineering Behind Training a 2 Trillion Parameter LLM
23.2K views2 months ago
YouTubePY
1:06:39
Lazy and Fast: Ranges Meet Parallelism in C++ - Daniel Anderson - CppCon 2025
7.9K views5 months ago
YouTubeCppCon
1:59:34
Parallelism in English Grammar | Basic to Advanced | Bank Exams 2026 | English by Anubhav Sir
57.1K views5 months ago
YouTubeAdda247
See more
Static thumbnail place holder