Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
pytorch
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Discriminative Fine-Tuning: Why Your Backbone and Your Head Shouldn't Learn at the Same Speed
Dai Nguyen
Dai Nguyen
Dai Nguyen
Follow
Sep 18
Discriminative Fine-Tuning: Why Your Backbone and Your Head Shouldn't Learn at the Same Speed
#
machinelearning
#
computervision
#
deeplearning
#
pytorch
Comments
Add Comment
6 min read
DeepSpeed ZeRO vs PyTorch FSDP2, Measured: 1.8x on NVLink, Barely Finishing on PCIe (Plus How to Actually Get GPUs on GKE)
Sho Tanaka (tsho)
Sho Tanaka (tsho)
Sho Tanaka (tsho)
Follow
Sep 17
DeepSpeed ZeRO vs PyTorch FSDP2, Measured: 1.8x on NVLink, Barely Finishing on PCIe (Plus How to Actually Get GPUs on GKE)
#
machinelearning
#
pytorch
#
deepspeed
#
gpu
Comments
Add Comment
10 min read
Undefined type Float8_e4m3fn on Apple Silicon: BF16 and GGUF Workarounds for FP8 Models
ACS Developer
ACS Developer
ACS Developer
Follow
Sep 14
Undefined type Float8_e4m3fn on Apple Silicon: BF16 and GGUF Workarounds for FP8 Models
#
macos
#
pytorch
#
ai
#
machinelearning
Comments
1
 comment
4 min read
OpenArch: PyTorch implementations of modern LLM architectures!
Mariano Gobea Alcoba
Mariano Gobea Alcoba
Mariano Gobea Alcoba
Follow
Sep 14
OpenArch: PyTorch implementations of modern LLM architectures!
#
pytorch
#
llm
#
deeplearning
#
neuralnetworks
Comments
Add Comment
5 min read
Installing PyTorch with ROCm Acceleration on Ubuntu 24.04
Sanskriti Harmukh
Sanskriti Harmukh
Sanskriti Harmukh
Follow
for
Vultr
Sep 16
Installing PyTorch with ROCm Acceleration on Ubuntu 24.04
#
pytorch
#
rocm
#
machinelearning
#
ubuntu
6
 reactions
Comments
Add Comment
2 min read
SSRF in PyTorch: How a Missing URL Validation in Dataset Loading Could Leak Cloud Credentials
stmanst
stmanst
stmanst
Follow
Sep 9
SSRF in PyTorch: How a Missing URL Validation in Dataset Loading Could Leak Cloud Credentials
#
security
#
python
#
ssrf
#
pytorch
Comments
Add Comment
2 min read
Neural Networks: Weights, Activation, and Backpropagation
Aahan-Chauhan
Aahan-Chauhan
Aahan-Chauhan
Follow
Sep 6
Neural Networks: Weights, Activation, and Backpropagation
#
machinelearning
#
beginners
#
deeplearning
#
pytorch
Comments
Add Comment
5 min read
PyTorch 2.14: clamp's Boundary Gradient Silently Changes, bfloat16 Complex Promotion Now Raises, cholesky/qr Removed
Sho Tanaka (tsho)
Sho Tanaka (tsho)
Sho Tanaka (tsho)
Follow
Sep 17
PyTorch 2.14: clamp's Boundary Gradient Silently Changes, bfloat16 Complex Promotion Now Raises, cholesky/qr Removed
#
machinelearning
#
pytorch
#
python
Comments
Add Comment
4 min read
What Your Loss Function Actually Tells the Model: MSE, Cross-Entropy, and the softmax Bug That Trains Anyway
Wesam Khallaf — Author of PyTorch From Ground Up
Wesam Khallaf — Author of PyTorch From Ground Up
Wesam Khallaf — Author of PyTorch From Ground Up
Follow
Sep 8
What Your Loss Function Actually Tells the Model: MSE, Cross-Entropy, and the softmax Bug That Trains Anyway
#
pytorch
#
deeplearning
#
machinelearning
#
beginners
Comments
Add Comment
13 min read
What optimizer.step() Actually Does: One Step of SGD, Momentum and Adam by Hand
Wesam Khallaf — Author of PyTorch From Ground Up
Wesam Khallaf — Author of PyTorch From Ground Up
Wesam Khallaf — Author of PyTorch From Ground Up
Follow
Aug 28
What optimizer.step() Actually Does: One Step of SGD, Momentum and Adam by Hand
#
pytorch
#
deeplearning
#
machinelearning
#
beginners
Comments
1
 comment
10 min read
Backpropagation by Hand: Two Layers, a Pen, and Then Autograd Agrees
Wesam Khallaf — Author of PyTorch From Ground Up
Wesam Khallaf — Author of PyTorch From Ground Up
Wesam Khallaf — Author of PyTorch From Ground Up
Follow
Aug 23
Backpropagation by Hand: Two Layers, a Pen, and Then Autograd Agrees
#
pytorch
#
python
#
machinelearning
#
beginners
Comments
Add Comment
9 min read
Model DNA, Analyzed: Verifying 'From-Scratch' LLM Claims with Architecture, Tokenizer, and CKA (PyTorch)
ai maya
ai maya
ai maya
Follow
Aug 9
Model DNA, Analyzed: Verifying 'From-Scratch' LLM Claims with Architecture, Tokenizer, and CKA (PyTorch)
#
ai
#
llm
#
machinelearning
#
pytorch
Comments
Add Comment
6 min read
ResKV: Recovering Evicted Token Contributions via Residual KV Cache — LongBench 32/32
Chaeyeon Mia Lee
Chaeyeon Mia Lee
Chaeyeon Mia Lee
Follow
Aug 6
ResKV: Recovering Evicted Token Contributions via Residual KV Cache — LongBench 32/32
#
llm
#
machinelearning
#
performance
#
pytorch
Comments
Add Comment
6 min read
Attention is simpler than you think - A hand-crafted superhero transformer
Tech-Aarvam
Tech-Aarvam
Tech-Aarvam
Follow
Sep 8
Attention is simpler than you think - A hand-crafted superhero transformer
#
ai
#
llm
#
pytorch
#
machinelearning
Comments
3
 comments
9 min read
Your quantized model got worse, and nothing told you
AS
AS
AS
Follow
Aug 2
Your quantized model got worse, and nothing told you
#
flutter
#
dart
#
machinelearning
#
pytorch
3
 reactions
Comments
2
 comments
5 min read
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account