[go: up one dir, main page]

DEV Community

#gpu

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why Does Your Local Model Crash at 32k Tokens?
eryk_kubiak_c9663554a1ff4 profile

Why Does Your Local Model Crash at 32k Tokens?

#llm #gpu #quantization #machinelearning
Comments 1
12 min read
Same Source, Two Cost Curves: Local Preview vs GPU Final
nidheeshdas profile

Same Source, Two Cost Curves: Local Preview vs GPU Final

#video #gpu #performance #devops
Comments
5 min read
Let your AI agent rent a GPU: llms.txt, --json and --budget
lium_io profile
Lium for Lium

Let your AI agent rent a GPU: llms.txt, --json and --budget

#ai #agents #gpu #devops
1
Comments 1
4 min read
Evaluating Multi-Node LLM Orchestrators: Exo, GPUStack, and LocalAI
rammehta1899 profile

Evaluating Multi-Node LLM Orchestrators: Exo, GPUStack, and LocalAI

#llm #platformengineering #infrastructure #gpu
Comments
1 min read
How Much VRAM Do You Really Need to Run a 70B LLM?
peter_gedeon profile

How Much VRAM Do You Really Need to Run a 70B LLM?

#ai #llm #gpu #ram
Comments
7 min read
Same nvJPEG2000, different numbers: timer boundaries and frames in flight
fastvideo profile

Same nvJPEG2000, different numbers: timer boundaries and frames in flight

#cuda #gpu #performance #cpp
Comments
13 min read
Exploring Result Visibility of Fixed-Latency Instructions on the SM120 Architecture
comradepenguin1917 profile

Exploring Result Visibility of Fixed-Latency Instructions on the SM120 Architecture

#cuda #nvidia #gpu
1
Comments
10 min read
Why GPU Availability Is Still the Biggest Bottleneck in ML Infra
sumukh_dev profile

Why GPU Availability Is Still the Biggest Bottleneck in ML Infra

#machinelearning #infrastructure #gpu #devops
1
Comments 1
3 min read
DeepSpeed ZeRO vs PyTorch FSDP2, Measured: 1.8x on NVLink, Barely Finishing on PCIe (Plus How to Actually Get GPUs on GKE)
tsho profile

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
10 min read
Half of my FP8 convolutions were silently running in f32 – a one-line XLA fix
retretor profile

Half of my FP8 convolutions were silently running in f32 – a one-line XLA fix

#machinelearning #performance #compilers #gpu
2
Comments 1
6 min read
What Happens When You Ask an LLM a Question
vishnuhd profile

What Happens When You Ask an LLM a Question

#ai #localllm #llmbasics #gpu
Comments
8 min read
CUDA Cores vs Tensor Cores Explained
sumukh_dev profile

CUDA Cores vs Tensor Cores Explained

#gpu #machinelearning #deeplearning #beginners
Comments 1
2 min read
Inside SFPU Overflow Bugs: How a 40-Year-Old Rounding Trick Breaks on Modern AI Accelerators
truongsontung profile

Inside SFPU Overflow Bugs: How a 40-Year-Old Rounding Trick Breaks on Modern AI Accelerators

#ai #machinelearning #gpu #debugging
Comments
3 min read
I Put a Paid AI Video Generator on My Own Gaming GPU — No Cloud Bill
ernioiu8 profile

I Put a Paid AI Video Generator on My Own Gaming GPU — No Cloud Bill

#ai #gpu #selfhosting #machinelearning
Comments 1
3 min read
Reverse-Engineering NVIDIA: Modifying a CUDA binary
stjepan86 profile

Reverse-Engineering NVIDIA: Modifying a CUDA binary

#nvidia #gpu #cuda #hex
Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.