shashankStack
/blog
/logs
/tags
/projects
/research
/talks
/about
/contact
/home
/blog
/logs
/tags
/projects
/research
/talks
/about
/contact
Tags
llm
(4)
pytorch
(3)
cuda
(2)
writing
(2)
tensors
(2)
linear-algebra
(2)
machine-learning
(2)
transformers
(2)
kv-cache
(2)
inference
(2)
metal
(1)
gpu
(1)
parallel-programming
(1)
nvcc
(1)
colab
(1)
pretraining
(1)
midtraining
(1)
posttraining
(1)
data-quality
(1)
synthetic-data
(1)
dpo
(1)
energy-based-model
(1)
likelihood
(1)
score-matching
(1)
diffusion
(1)
personal-growth
(1)
webdev
(1)
side-project
(1)
attention
(1)
deepseek
(1)
mla
(1)
agents
(1)
workflow
(1)
expertise
(1)
learning
(1)
optimization
(1)