
SDE 1 @Pure Billion Technologies | Full Stack Developer | Freelancer
Joined July 2017
- Tweets827
- Following326
- Followers308
- Likes3.6K
Pranit Patil retweeted
Depth-aware light injection in TypeGPU
I got a 448x448 monocular depth model down to ~8 ms on my M4 Pro across ~250 dispatches, which is fast enough to use in realtime :D
Since the inference is written directly in TypeGPU, I can just feed the depth buffer straight into the lighting pass. It never has to leave the GPU or go through any extra synchronization/interop step
Inference, lighting and draw all go through the same command encoder.
Replying to @ChanchalKamini
I believe in stealing from office parties rather than saving ☺️
Pranit Patil retweeted
Ek Developer Vibe Coder ban sakta hai !
But
Ek Vibe Coder kabhi developer nahi ban sakta !
Pranit Patil retweeted
Introducing TurboQuant: Our new compression algorithm that reduces LLM key-value cache memory by at least 6x and delivers up to 8x speedup, all with zero accuracy loss, redefining AI efficiency. Read the blog to learn how it achieves these results: goo.gle/4bsq2qI
Replying to @mysticwillz
Ideally we use refresh tokens flow and jwt expires in 5 mins. Another thing we can do is we can maintain the token blacklist in the redis.
Replying to @arpit_bhayani
Hashmap + RESP protocol and you are done
Replying to @krishnadotdev @SumitM_X
You can use an inverted index for that










