Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
Follow
User actions
Yuvraj singh Bhadoria
404 bio not found
Joined
Joined on
Aug 29, 2026
More info about @yuvraj_llminference
Post
5 posts published
Comment
0 comments written
Tag
4 tags followed
Demystifying Speculative Decoding: From Architecture to Production Bottlenecks
Yuvraj singh Bhadoria
Yuvraj singh Bhadoria
Yuvraj singh Bhadoria
Follow
Aug 30
Demystifying Speculative Decoding: From Architecture to Production Bottlenecks
#
llm
#
machinelearning
#
performance
#
inference
Comments
Add Comment
8 min read
Demystifying Speculative Decoding: From Architecture to Production Bottlenecks
Yuvraj singh Bhadoria
Yuvraj singh Bhadoria
Yuvraj singh Bhadoria
Follow
Aug 30
Demystifying Speculative Decoding: From Architecture to Production Bottlenecks
#
llm
#
machinelearning
#
performance
#
inference
Comments
Add Comment
8 min read
Demystifying Speculative Decoding: From Architecture to Production Bottlenecks
Yuvraj singh Bhadoria
Yuvraj singh Bhadoria
Yuvraj singh Bhadoria
Follow
Aug 30
Demystifying Speculative Decoding: From Architecture to Production Bottlenecks
#
llm
#
inference
#
machinelearning
#
performance
Comments
Add Comment
8 min read
KV-Cache Quantization: How 2–4 Bits Cut LLM Memory by 4–8 Without Killing Quality
Yuvraj singh Bhadoria
Yuvraj singh Bhadoria
Yuvraj singh Bhadoria
Follow
Aug 29
KV-Cache Quantization: How 2–4 Bits Cut LLM Memory by 4–8 Without Killing Quality
Comments
Add Comment
8 min read
I Wrote the Three Attention Kernels That Run LLM Inference — in Portable Triton, on a Free Colab T4
Yuvraj singh Bhadoria
Yuvraj singh Bhadoria
Yuvraj singh Bhadoria
Follow
Aug 29
I Wrote the Three Attention Kernels That Run LLM Inference — in Portable Triton, on a Free Colab T4
1
reaction
Comments
Add Comment
6 min read
loading...
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account