Rohan

@suneruperera @krishgarg @GoogleDeepMind w garg ❤️‍🩹

@krishgarg @GoogleDeepMind Holy W Garg🔥🔥

i just beat @GoogleDeepMind's turboquant introducing Shard. 10x KV cache compression on Llama-3.1-8B. zero quality loss - 10x @ 8K context, 11.2x @ 32K - NIAH recall 1.000 across 4K-32K - LongBench Δ ≈ 0 vs FP16 turboquant tops out at 4-6x at the same quality. we doubled it. read more: krishgarg.com/shard @kirrithan

3D reconstruction stands as one of the most prevalent problems in the CV space. Made a NeRF from scratch to learn more. Optimized across 2× NVIDIA T4 GPUs with F16 mixed-precision with @runpod. Peeked @ PSNR of 22, video pinned below!

FSDLJKFHLDJSKAHFKJL

@adeel_712 @ollama Tuff

i built a free way to index and search any docs locally (cli or mcp) with a memory layer runs entirely on your machine via @ollama

@yasbehiri @kabirj_25 @selimaz_ @ericzhu @AlexSomtingwang

went to sf. thought it’d be fun. got called an indian lesbian. came back.