$/BY DDPANDA/9 MIN READ/1,891 WORDS
Master LLM Inference Engineering (Phase 1) : Foundations & Optimization
Source: https://inference.vizuara.ai/Phase 1 — Foundations & Optimization
- 7 core lectures
- Hardware lab sessions included
- Daily Colab labs & visual guides
- Live Zoom sessions + recordings
- The Inference Stack
- Full pipeline, tokenization, forward pass, autoregressive loop
- Transformer Deep Dive
- Attention (MHA/MQA/GQA), embeddings, positional encoding
- Prefill, Decode & KV Cache
- KV cache mechanics, chunked prefill, prefix caching, prompt caching. KV cache compression: GQA, token eviction, H2O, StreamingLLM
- GPU Architecture & Roofline
- SMs, tensor cores, compute vs. memory bound
- Quantization
- FP16, BF16, INT8, INT4, GPTQ, AWQ, GGUF format
- Speculative Decoding
- Draft-target, n-gram, EAGLE, Medusa, acceptance sampling
- FlashAttention, Kernel Fusion & Inference Engines
- IO-aware tiling, online softmax, fused kernels. PagedAttention, continuous/dynamic/in-flight batching, vLLM scheduler internals. Engines: vLLM, SGLang, TensorRT-LLM
Archive File List
# Modified Size Packed Name # # [FkcbobkzbBkdfkbbo[ddpanda].rar 2026-08-01 11:11 258493664 258493664 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\1. The Vizuara Inference Book Phase 1 ( Also your lecture notes!)\convolution-musical-journey-main.zip 2026-08-01 11:18 65 80 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\1. The Vizuara Inference Book Phase 1 ( Also your lecture notes!)\Links.txt 2026-08-01 11:04 207949145 207949152 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\1. The Vizuara Inference Book Phase 1 ( Also your lecture notes!)\Vizuara Inference Book Phase 1.pdf 2026-08-01 13:13 25591112 25591120 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\10. Lecture 6 The anatomy of a vLLM Step\anatomy-of-a-vllm-step.pdf 2026-08-02 21:34 435389780 435389792 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\10. Lecture 6 The anatomy of a vLLM Step\Lecture 6.mp4 2026-08-01 13:15 538 544 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\10. Lecture 6 The anatomy of a vLLM Step\Links.txt 2026-08-02 23:28 560382370 560382384 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\11. Lecture 7 All about Quantization\Lecture 7.mp4 2026-08-01 13:18 422 432 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\11. Lecture 7 All about Quantization\Links.txt 2026-08-03 00:52 420149469 420149472 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\12. Lecture 8 Speculative Decoding\Lecture 8.mp4 2026-08-01 13:20 330 336 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\12. Lecture 8 Speculative Decoding\Links.txt 2026-06-10 02:42 1203409 1203424 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\13. Phase 1 Capstone Project!\Inference Engg Capstone Project 1 Submissions\capstone_report_v4_inference_newest.pdf 2026-06-10 02:41 12482328 12482336 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\13. Phase 1 Capstone Project!\Inference Engg Capstone Project 1 Submissions\InferTutor Arena - Manoj.pdf 2026-06-10 02:42 896350 896352 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\13. Phase 1 Capstone Project!\Inference Engg Capstone Project 1 Submissions\InferTutor-Arena-Experiments-Report-Anindya-Saha.pdf 2026-08-01 13:24 63335153 63335168 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\13. Phase 1 Capstone Project!\Inference Engineering Phase 1 Final Lecture.mp4 2026-08-01 13:26 54 64 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\13. Phase 1 Capstone Project!\Links.txt 2026-08-02 01:38 251947836 251947840 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\2. Hardware Labs\Hardware Labs 1 Video Recording - Mobile Phone LLM Inference.mp4 2026-08-02 02:40 58179742 58179744 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\2. Hardware Labs\Hardware Labs 2 Video Recording.mp4 2026-08-02 03:03 42802855 42802864 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\2. Hardware Labs\Hardware Labs 3 Video Recording.mp4 2026-08-01 11:41 113080 113088 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\2. Hardware Labs\infertutor-arena-capstone-main.zip 2026-08-01 11:44 322 336 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\2. Hardware Labs\Links.txt 2026-08-01 11:41 72346 72352 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\2. Hardware Labs\Raspberry_Pi_Inference_Lab_Module.pdf 2026-08-01 11:39 655286 655296 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\2. Hardware Labs\Vizuara_AI_Jetson_Orin_Nano_Setup_Guide_ (1).pdf 2026-08-01 11:44 80 80 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\3. All Visual Walkthroughs in one place\Links.txt 2026-08-02 03:11 651455426 651455440 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\4. Lecture 1 Introduction to Inference Engineering\Lecture 1.mp4 2026-08-01 11:58 407 416 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\4. Lecture 1 Introduction to Inference Engineering\Links.txt 2026-08-01 12:07 26788 26800 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\1.Good and Evil of KV Cache_L02_KV_Cache_Demo.ipynb 2026-08-01 12:07 875063 875072 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\2.TurboQuant KV Cache_L02_KV_Cache_Demo_TurboQuant.ipynb 2026-08-01 12:28 58185 58192 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\01_introduction.ipynb 2026-08-01 12:30 52898 52912 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\02_section_1_the_gpu_has_two_masters_vram_a.ipynb 2026-08-01 12:31 64020 64032 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\03_section_2_the_naive_inference_loop_an_o_.ipynb 2026-08-01 12:31 51866 51872 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\04_section_3_enter_the_kv_cache_the_hero_we.ipynb 2026-08-01 12:32 70405 70416 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\05_section_4_the_hidden_cost_what_the_kv_ca.ipynb 2026-08-01 12:33 74116 74128 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\06_section_5_living_with_the_necessary_evil.ipynb 2026-08-01 12:33 68882 68896 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\07_section_6_turboquant_rotating_your_way_t.ipynb 2026-08-01 12:34 57067 57072 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\08_the_full_picture.ipynb 2026-08-01 12:34 65669 65680 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\09_further_reading.ipynb 2026-08-01 12:25 5116482 5116496 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\Article - The Good and Evil of the Key-Value Cache.png 2026-08-01 12:37 100510 100512 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\Case Study - Build It.png 2026-08-01 12:40 163 176 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\Case Study - Colab.url 2026-08-01 12:37 1237654 1237664 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\Case Study - Production Design.png 2026-08-01 12:36 1113655 1113664 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\Case Study - Technical Formulation.png 2026-08-01 12:36 546420 546432 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\Case Study - The Problem.png 2026-08-01 12:35 4264 4272 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods\Practice with Notebooks.txt 2026-08-02 05:47 541627015 541627024 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Lecture 2.mp4 2026-08-01 12:26 304 304 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Links.txt 2026-08-02 08:42 186345993 186346000 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\6. Bonus Lecture Inference and YCombinator\Bonus Lecture.mp4 2026-08-01 12:47 157 160 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\6. Bonus Lecture Inference and YCombinator\Links.txt 2026-08-01 12:52 29890 29904 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\7. Lecture 3 Attention Variants Part 1 (MHA, MQA, GQA, Latent Attention, Sparse Attention)\Clean_KV_Cache_Inference_Benchmark_MHA_GQA_MQA_MLA.ipynb 2026-08-02 09:09 561905275 561905280 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\7. Lecture 3 Attention Variants Part 1 (MHA, MQA, GQA, Latent Attention, Sparse Attention)\Lecture 3.mp4 2026-08-01 12:58 1042 1056 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\7. Lecture 3 Attention Variants Part 1 (MHA, MQA, GQA, Latent Attention, Sparse Attention)\Links.txt 2026-08-01 12:52 14705 14720 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\7. Lecture 3 Attention Variants Part 1 (MHA, MQA, GQA, Latent Attention, Sparse Attention)\run_tinystories_kv_benchmark.py 2026-08-02 18:37 626257287 626257296 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\8. Lecture 4 Attention Variants Part 2 (Sliding Window, State Space Models and Mamba)\Lecture 4.mp4 2026-08-01 13:06 1135 1136 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\8. Lecture 4 Attention Variants Part 2 (Sliding Window, State Space Models and Mamba)\Links.txt 2026-08-02 20:23 537281183 537281184 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\9. Lecture 5 All about Flash Attention 1, 2, 3\Lecture 5.mp4 2026-08-01 13:10 397 400 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\9. Lecture 5 All about Flash Attention 1, 2, 3\Links.txt 2026-08-01 13:09 441584 441584 [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\9. Lecture 5 All about Flash Attention 1, 2, 3\Vizuara_AI_Labs_FlashAttention_Benchmark_RunPod_Executed.ipynb 2026-08-01 13:29 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\13. Phase 1 Capstone Project!\Inference Engg Capstone Project 1 Submissions 2026-08-01 12:40 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache\Assignment KV Cache Pods 2026-08-01 11:18 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\1. The Vizuara Inference Book Phase 1 ( Also your lecture notes!) 2026-08-03 22:41 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\10. Lecture 6 The anatomy of a vLLM Step 2026-08-03 22:41 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\11. Lecture 7 All about Quantization 2026-08-03 22:41 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\12. Lecture 8 Speculative Decoding 2026-08-01 13:30 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\13. Phase 1 Capstone Project! 2026-08-03 22:37 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\2. Hardware Labs 2026-08-03 22:37 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\3. All Visual Walkthroughs in one place 2026-08-03 22:41 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\4. Lecture 1 Introduction to Inference Engineering 2026-08-03 22:41 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\5. Lecture 2 Good and Evil of KV Cache 2026-08-03 22:42 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\6. Bonus Lecture Inference and YCombinator 2026-08-03 22:41 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\7. Lecture 3 Attention Variants Part 1 (MHA, MQA, GQA, Latent Attention, Sparse Attention) 2026-08-03 22:41 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\8. Lecture 4 Attention Variants Part 2 (Sliding Window, State Space Models and Mamba) 2026-08-03 22:41 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization\9. Lecture 5 All about Flash Attention 1, 2, 3 2026-08-03 22:41 Folder Folder [Inference Engineering Workshop] Phase 1 only Foundations & Optimization # # Total Size Packed Files # 5454591643 5454592112 72
Download Links [PAID]
Password: cms.ddpanda.org