corpus.blog
56,966 blogs · [ { "id": "01a087e8-3ed6-73f2-8e4f-e933b52a57b1", "title": "MCP in production", "url": "https://sushant-kumar.com/blog/mcp-production", "published_at": "2026-06-21T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933b5c936b1", "title": "Understanding GPT-OSS architecture", "url": "https://sushant-kumar.com/blog/gpt-oss", "published_at": "2025-08-06T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933b6a96030", "title": "Normalization Techniques in Transformer-Based LLMs: LayerNorm, RMSNorm, and Beyond", "url": "https://sushant-kumar.com/blog/normalization-in-transformer-based-llms", "published_at": "2025-07-26T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933b786026c", "title": "Model Context Protocol (MCP): The USB-C of AI Integrations", "url": "https://sushant-kumar.com/blog/model-context-protocol", "published_at": "2025-06-16T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933b7f20f4f", "title": "RAG Techniques - OpenAI API + Qdrant", "url": "https://sushant-kumar.com/blog/rag-techniques", "published_at": "2025-05-06T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933b8b00dca", "title": "Training LLMs on GPUs", "url": "https://sushant-kumar.com/blog/training-llms-on-gpus", "published_at": "2024-11-30T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933b95d89fc", "title": "How AI monitors calls of 5,000+ sales representatives for actionable insights", "url": "https://sushant-kumar.com/blog/ai-sales-monitoring", "published_at": "2024-11-23T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933b970a9a3", "title": "The Path to the Ultimate Prize", "url": "https://sushant-kumar.com/blog/path-to-prize", "published_at": "2024-11-22T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933ba0b69a2", "title": "Vision Transformers", "url": "https://sushant-kumar.com/blog/vision-transformers", "published_at": "2024-10-14T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933ba2fbb71", "title": "Paligemma: Versatile VLM - Vision Language Models", "url": "https://sushant-kumar.com/blog/paligemma", "published_at": "2024-10-11T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933baf5698b", "title": "SigLIP: Sigmoid Loss in Language Image Pretraining", "url": "https://sushant-kumar.com/blog/siglip", "published_at": "2024-10-06T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933bb01b650", "title": "Whisper: Transformer for Speech Recognition", "url": "https://sushant-kumar.com/blog/whisper", "published_at": "2024-05-07T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933bb224400", "title": "Phi 3: Highly Capable Language Model on Phone", "url": "https://sushant-kumar.com/blog/phi3", "published_at": "2024-05-02T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933bb940f9b", "title": "LLaVA: Large Multimodal Model", "url": "https://sushant-kumar.com/blog/llava", "published_at": "2024-04-30T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933bc45e312", "title": "Llama 3: SOTA open-weights LLM", "url": "https://sushant-kumar.com/blog/llama3", "published_at": "2024-04-23T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933bcb2b563", "title": "Grouped Query Attention", "url": "https://sushant-kumar.com/blog/grouped-query-attention", "published_at": "2024-04-16T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933bd2cb45e", "title": "RoPE: Rotary Positional Embedding", "url": "https://sushant-kumar.com/blog/rope-rotary-positional-embedding", "published_at": "2024-04-16T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933bd8c04de", "title": "Multi Query Attention", "url": "https://sushant-kumar.com/blog/multi-query-attention", "published_at": "2024-04-13T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933be52b030", "title": "Gemma: Google's family of Open LLMs", "url": "https://sushant-kumar.com/blog/gemma", "published_at": "2024-04-12T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933bf410646", "title": "How Stable Diffusion works", "url": "https://sushant-kumar.com/blog/stable-diffusion", "published_at": "2024-04-11T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933bfafdec3", "title": "CLIP: Bridging Vision and Language in AI", "url": "https://sushant-kumar.com/blog/clip", "published_at": "2024-04-10T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933c04ede6e", "title": "Mixtral of Experts", "url": "https://sushant-kumar.com/blog/mixtral-of-experts", "published_at": "2024-04-09T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933c06f9498", "title": "MoE: Mixture of Experts", "url": "https://sushant-kumar.com/blog/mixture-of-experts", "published_at": "2024-04-08T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933c0ff4eca", "title": "RAG Triad - Evaluating Quality of Response from LLMs", "url": "https://sushant-kumar.com/blog/rag-triad", "published_at": "2024-04-08T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933c15023c3", "title": "DDPM: Denoising Diffusion Probabilistic Models", "url": "https://sushant-kumar.com/blog/ddpm-denoising-diffusion-probabilistic-models", "published_at": "2024-03-23T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933c1734e8d", "title": "GPT-2: A Deep Dive", "url": "https://sushant-kumar.com/blog/gpt2", "published_at": "2024-03-22T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933c180c3af", "title": "BERT: Bidirectional Encoder Representations from Transformers", "url": "https://sushant-kumar.com/blog/bert", "published_at": "2024-03-21T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933c224352c", "title": "Transformers: Attention is All You Need", "url": "https://sushant-kumar.com/blog/transformers", "published_at": "2024-03-20T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933c2ddd5f5", "title": "Tokenization in Large Language Models", "url": "https://sushant-kumar.com/blog/tokenization-in-large-language-models", "published_at": "2024-03-19T00:00:00+00:00" }, { "id": "01a087e8-3ed6-73f2-8e4f-e933c365d835", "title": "VAE: Variational Autoencoder", "url": "https://sushant-kumar.com/blog/vae-variational-autoencoder", "published_at": "2024-03-18T00:00:00+00:00" } ] posts Claim your blog
Back to sushant-kumar.com
Blog · corpus.blog/blogs/sushant-kumar.com/posts

sushant-kumar.com

sushant-kumar.com

2026

MCP in productionoriginal ↗
21 Jun 2026

2025

Understanding GPT-OSS architectureoriginal ↗
6 Aug 2025
Normalization Techniques in Transformer-Based LLMs: LayerNorm, RMSNorm, and Beyondoriginal ↗
26 Jul 2025
Model Context Protocol (MCP): The USB-C of AI Integrationsoriginal ↗
16 Jun 2025
RAG Techniques - OpenAI API + Qdrantoriginal ↗
6 May 2025

2024

Training LLMs on GPUsoriginal ↗
30 Nov 2024
How AI monitors calls of 5,000+ sales representatives for actionable insightsoriginal ↗
23 Nov 2024
The Path to the Ultimate Prizeoriginal ↗
22 Nov 2024
Vision Transformersoriginal ↗
14 Oct 2024
Paligemma: Versatile VLM - Vision Language Modelsoriginal ↗
11 Oct 2024
SigLIP: Sigmoid Loss in Language Image Pretrainingoriginal ↗
6 Oct 2024
Whisper: Transformer for Speech Recognitionoriginal ↗
7 May 2024
Phi 3: Highly Capable Language Model on Phoneoriginal ↗
2 May 2024
LLaVA: Large Multimodal Modeloriginal ↗
30 Apr 2024
Llama 3: SOTA open-weights LLMoriginal ↗
23 Apr 2024
Grouped Query Attentionoriginal ↗
16 Apr 2024
RoPE: Rotary Positional Embeddingoriginal ↗
16 Apr 2024
Multi Query Attentionoriginal ↗
13 Apr 2024
Gemma: Google's family of Open LLMsoriginal ↗
12 Apr 2024
How Stable Diffusion worksoriginal ↗
11 Apr 2024
CLIP: Bridging Vision and Language in AIoriginal ↗
10 Apr 2024
Mixtral of Expertsoriginal ↗
9 Apr 2024
MoE: Mixture of Expertsoriginal ↗
8 Apr 2024
RAG Triad - Evaluating Quality of Response from LLMsoriginal ↗
8 Apr 2024
DDPM: Denoising Diffusion Probabilistic Modelsoriginal ↗
23 Mar 2024
GPT-2: A Deep Diveoriginal ↗
22 Mar 2024
BERT: Bidirectional Encoder Representations from Transformersoriginal ↗
21 Mar 2024
Transformers: Attention is All You Needoriginal ↗
20 Mar 2024
Tokenization in Large Language Modelsoriginal ↗
19 Mar 2024
VAE: Variational Autoencoderoriginal ↗
18 Mar 2024