Nagi Reddy

🇮🇳

[Nagi Reddy @NiteeshBv]

Back with bang! Bang!

[Nagi Reddy @NiteeshBv]

@KyeGomezB @nvidia @Kimi_Moonshot @swarms_corp Great work 👍

[Praveen Kumar Verma @Alacritic_Super]

15 AI Research Papers Every AI Engineer Should Read

1. Attention Is All You Need (Transformers)
https://t.co/uNqD7WesTy

2. LoRA: Low-Rank Adaptation
https://t.co/7OfFr3JksJ

3. PEFT (Parameter-Efficient Fine-Tuning)
https://t.co/sT7HVw2Mux

4. An Image is Worth 16×16 Words (Vision Transformer)
https://t.co/JsgvilnrtM

5. Auto-Encoding Variational Bayes (VAE)
https://t.co/VDa7oD9xtT

6. Generative Adversarial Networks (GANs)
https://t.co/ZDW8H6lPOS

7. BERT
https://t.co/IqdUwr9w0n

8. High-Resolution Image Synthesis with Latent Diffusion Models
https://t.co/g3B2DtV0we

9. Retrieval-Augmented Generation (RAG)
https://t.co/Bkhg7OvtRx

10. Language Models are Few-Shot Learners (GPT-3)
https://t.co/bTNvpzFffw

11. Switch Transformers (MoE)
https://t.co/n2hpgHw6Ri

12. Learning to Summarize with Human Feedback (RLHF)
https://t.co/Xi7BLjbBQg

13. LLaMA: Open and Efficient Foundation Language Models
https://t.co/A8zfwaKroJ

14. RoFormer: Rotary Position Embedding (RoPE)
https://t.co/5vHovvUrl7

15. InstructGPT
https://t.co/METMZVuqxI

Reading papers is one thing. Understanding why each changed the field is what makes you a stronger AI engineer.

[Praveen Kumar Verma @Alacritic_Super]

Want to master LLM Cache Management? Start with these resources.

KV Cache: https://t.co/ma0FgKaEiy
https://t.co/m3SOyopgJ4

Prefix Caching https://t.co/QW4eve0J7M

Continuous Batching https://t.co/yLT29dzS8R

Speculative Decoding https://t.co/BSxfeG75AG

KV Cache Quantization https://t.co/UrXb95bwZy

Research Papers:

1. FlashInfer (Attention Engine) https://t.co/MabtUlqNXq
2. Zipage (Compressed PagedAttention) https://t.co/Ca7JZuz6h7
3. IceCache (Memory-Efficient KV Cache) https://t.co/pm4YNcIjHY

[voxium @v0xium]

I strongly recommend reading the Transformer chapter from Speech and Language Processing by Dan Jurafsky and James H. Martin.

The book is freely available, and is one of the best resources if you want to understand the mathematics behind LLMs.

[Devpost @devpost]

That app idea you've had for months? Time to dust it off and actually ship it. RevenueCat's Shipaton is back and they're giving you two months to take it from idea to product with a shot at prizes worth up to $1M! 🤯

[Nagi Reddy @NiteeshBv]

@oopssunnyy Hi There..... 😀

[Nagi Reddy @NiteeshBv]

@AbhinavXJ I also have small doubt. If i have 1 GB file. I upload in GCP, AWS or Azure. This cloud providers don't save 1 GB as same as per me. The have good comparison algorithm.

I don't know which algorithm or approach, how the achive.

If you have any information. Please let me know.

[Nagi Reddy @NiteeshBv]

@AbhinavXJ Good One. I have question?

I didn't understand. Why Google is copying data to all 3 chunk server s.

Which is same data every 3 servers. Y didn't the choose Eventually consistency to other 2 servers.

if the designed for 100% availablity and consistency. The fine.

[Deep Note @1DeepNote]

9 Netflix Documentaries That Can Change The Way You Think

1. Stutz

[Mehul Mohan @mehulmpt]

I believe 10 years down the line it would not be uncommon to buy AI intelligence in a new home, for an extra $400-$500k.

A centralised intelligence box/rack that every AI harness, including hardware/robots would use.

Talking about that future a bit in a video today.

[Anas @Anas_is_me]

You don't need a college degree to think like a staff engineer.
This is a master curriculum mapping out the single best book and free lecture series for the 9 core pillars of CS (OS, Networking, Databases, Distributed Systems).
Save this for later: https://t.co/1TzxXnD3Z0

[BookVerse @BookInsider_91]

5 Powerful lessons from " Fall in love with the problem not the solution"

[Jia-Bin Huang @jbhuang0604]

LoRA, low-rank adaptation, is arguably the most popular parameter-efficient fine-tuning method for LLMs.

But how does it actually work?

Check out the video to learn LoRA and friends (LoRA+, QLoRA, VeRA, and DoRA)!

https://t.co/v9qFegbK7g

[Neo Kim @systemdesignone]

Arguably the 20 most influential books for software engineers.

Most of us spent years on a CS degree and were assigned almost none of them.

1 The Pragmatic Programmer
2 Designing Data-Intensive Applications
3 Clean Code
4 The Mythical Man-Month
5 Refactoring: Improving the Design of Existing Code
6 Working Effectively with Legacy Code
7 Software Architecture: The Hard Parts
8 Database Internals
9 Staff Engineer: Leadership Beyond the Management Track
10 Extreme Ownership: How U.S. Navy SEALs Lead and Win
11 A Philosophy of Software Design
12 Why Programs Fail: A Guide to Systematic Debugging
13 Code Complete
14 Introduction to Algorithms
15 The C Programming Language
16 The Art of Computer Programming, Volume 1: Fundamental Algorithms
17 Building Microservices: Designing Fine-Grained Systems
18 Structure and Interpretation of Computer Programs
19 Peopleware: Productive Projects and Teams
20 Design Patterns: Elements of Reusable Object-Oriented Software

How many have you read?

[Igor De Souza @Igfasouza]

Foundations of Distributed Streaming: A Book Review of “Kafka for Architects”

#apachekafka

https://t.co/dm2WzpLBlW

[Hussein Nasser @hnasr]

Root Cause will make you look and think of system internals from a different lens.

Grab your copy

Amazon:
https://t.co/flopo4GN73

b&n
https://t.co/gz4usDugsn

[Ben Dicken @BenjDicken]

Remember that time @brendangregg shouted at hard drives to make them slower?

Someone please confirm nvme ssd is immune.

[AshutoshShrivastava @ai_for_success]

Take 136 seconds out of your day and listen to Sundar Pichai.

[Mrinal @Hi_Mrinal]

Okkay so everyone is sharing yt playlists now ... So I thought to post one of my favorite too

these have been my goto playlists while doing non serious stuffs . Just insane amount of learning tbh

1. https://t.co/qe8RI79P9M
2. https://t.co/YmIttZr57F
3.https://t.co/s1gURmWsT8

[Nagi Reddy @NiteeshBv]

@lokio_aj @udayan_w