athleticKoder's profile picture. ml @zomato; prev: ai consultant @google

anshuman

@athleticKoder

ml @zomato; prev: ai consultant @google

ปักหมุด

LoRA sounds simple: 1. Add low-rank matrices 2. Train with less memory 3. Get same results Reality: - Learning rate needs 10x adjustment - Layer selection changes everything - Batch size tolerance is different


Nano Banana Pro Understands somethings very well

athleticKoder's tweet image. Nano Banana Pro Understands somethings very well

nanobanana pro understands some things very well

HarveenChadha's tweet image. nanobanana pro understands some things very well


anshuman รีโพสต์แล้ว

dear Substack, I'm once again appealing for a stripe alternative in India yours truly.

athleticKoder's tweet image. dear Substack,

I'm once again appealing for a stripe alternative in India

yours truly.

okay so @1littlecoder recommended me @Patreon. has anyone tried it? what are your reviews. pros/cons? i am honestly fed up of non-existent support of substack. as my audience is growing i am looking to build a community. a good portion of my audience is willing to pay for stuff…

dear Substack, I'm once again appealing for a stripe alternative in India yours truly.

athleticKoder's tweet image. dear Substack,

I'm once again appealing for a stripe alternative in India

yours truly.


anshuman รีโพสต์แล้ว

Techniques to Master for Faster + Cheaper LLM Inference 1. Quantization (INT8/INT4/FP8) 2. KV-Cache Optimization (quantization, compression, eviction) 3. Flash Attention 4. Speculative Decoding 5. Continuous Batching 6. Paged Attention / vLLM-style memory management 7. Tensor…


Google is soo back.

athleticKoder's tweet image. Google is soo back.

Introducing Gemini 3 Pro, the world's most intelligent model that can help you being anything to life. It is state of the art across most benchmarks, but really comes to life across our products (AI Studio, the Gemini API, Gemini App, etc) 🤯

OfficialLoganK's tweet image. Introducing Gemini 3 Pro, the world's most intelligent model that can help you being anything to life. 

It is state of the art across most benchmarks, but really comes to life across our products (AI Studio, the Gemini API, Gemini App, etc) 🤯


we've been busy

athleticKoder's tweet image. we've been busy
athleticKoder's tweet image. we've been busy

Loading...

Something went wrong.


Something went wrong.