DEV Community

#gpu

Posts

πŸ‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
RTX 3090 vs A100 for a 7B model on vLLM: the cheaper GPU depends on your answer time
qaisermehdi profile

RTX 3090 vs A100 for a 7B model on vLLM: the cheaper GPU depends on your answer time

#vllm #llm #mlops #gpu
2 min read
Serving a 1B math model on vLLM: the memory cap sets how many answers fit, not how fast
inferencekeydev profile

Serving a 1B math model on vLLM: the memory cap sets how many answers fit, not how fast

#ai #llm #machinelearning #gpu
4 min read
Как я Π²ΠΏΠΈΡ…ΠΈΠ²Π°Π» Ρ‚Ρ€ΠΈ ΠΌΠΎΠ΄Π΅Π»ΠΈ Π² 6 Π“Π‘ видСопамяти
anxi0uz profile

Как я Π²ΠΏΠΈΡ…ΠΈΠ²Π°Π» Ρ‚Ρ€ΠΈ ΠΌΠΎΠ΄Π΅Π»ΠΈ Π² 6 Π“Π‘ видСопамяти

#python #machinelearning #llm #gpu
2
1
2 min read
LM Studio vs Ollama on an RTX 5080: The Settings Matter More Than the Wrapper
techfuelhq profile

LM Studio vs Ollama on an RTX 5080: The Settings Matter More Than the Wrapper

#localai #ollama #llm #gpu
5 min read
How I squeezed three models into 6 GB of VRAM
anxi0uz profile

How I squeezed three models into 6 GB of VRAM

#python #machinelearning #llm #gpu
2
2
6 min read
Fitting Flint's coding agent on a 24 GB RTX 4090: context is the knob that decides
inferencekeydev profile

Fitting Flint's coding agent on a 24 GB RTX 4090: context is the knob that decides

#ai #llm #gpu #selfhosted
5 min read
When Java 27 Removed JVMCI, TornadoVM Built Its Own Compiler
jamilxt profile

When Java 27 Removed JVMCI, TornadoVM Built Its Own Compiler

#java #ai #compilers #gpu
1
8 min read
GPU Info Processing Caused Performance Regression: Root Cause Identified and Resolved
serbyte profile

GPU Info Processing Caused Performance Regression: Root Cause Identified and Resolved

#gpu #performance #regression #optimization
11 min read
TensorRT Was Fast. My 1080p RTSP Pipeline Wasn't.
colaweb profile
Igor

TensorRT Was Fast. My 1080p RTSP Pipeline Wasn't.

#computervision #cuda #gpu #performance
5 min read
DePIN GPU Bubble Bursts: Render, Akash Utilization Slide Below 40% as Hyperscaler Prices Collapse
finpulse360_org profile

DePIN GPU Bubble Bursts: Render, Akash Utilization Slide Below 40% as Hyperscaler Prices Collapse

#depin #gpu #render #akash
4 min read
Running neural networks in a Unity editor tool with compute shaders
raphael_tan_9c17abd05a891 profile

Running neural networks in a Unity editor tool with compute shaders

#unity3d #gamedev #machinelearning #gpu
1
8 min read
The big clouds charge a median 3.2x the cheapest GPU rate: 18 GPUs compared
fastgpu profile

The big clouds charge a median 3.2x the cheapest GPU rate: 18 GPUs compared

#gpu #cloud #aws #machinelearning
1
5 min read
Real-CUGAN on Linux vs Windows: same flags, two NVIDIA GPUs, SSIM 0.9977
nefayran profile

Real-CUGAN on Linux vs Windows: same flags, two NVIDIA GPUs, SSIM 0.9977

#ai #linux #ffmpeg #gpu
4 min read
Nemotron 3.5 Bolt on one GPU: what the 24 GB covers, the drafter flag and the llama.cpp trap
inferencekeydev profile

Nemotron 3.5 Bolt on one GPU: what the 24 GB covers, the drafter flag and the llama.cpp trap

#ai #llm #gpu #opensource
2
5 min read
torch.compile vs eager for training a 468M Llama-style model on four GPUs: step time, memory and compile cost
runcrate profile

torch.compile vs eager for training a 468M Llama-style model on four GPUs: step time, memory and compile cost

#pytorch #machinelearning #gpu #python
5 min read
πŸ‘‹ Sign in for the ability to sort posts by relevant, latest, or top.