Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
gpu
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
2B Gemma 4 QAT Deployment with GCE, NVIDIA L4, MCP, and Antigravity CLI
xbill
xbill
xbill
Follow
for
Google Developer Experts
Jul 13
2B Gemma 4 QAT Deployment with GCE, NVIDIA L4, MCP, and Antigravity CLI
#
mcps
#
antigravitycli
#
gce
#
gpu
5
 reactions
Comments
Add Comment
15 min read
GPUs for AI in 2026: NVIDIA, AMD, Intel Compared
Rost
Rost
Rost
Follow
Jul 14
GPUs for AI in 2026: NVIDIA, AMD, Intel Compared
#
gpu
#
ai
#
nvidia
#
hardware
Comments
Add Comment
9 min read
Vulkan Computing with FP16 on PS4 GPU
Debarshi Sarkar (Deb.S)
Debarshi Sarkar (Deb.S)
Debarshi Sarkar (Deb.S)
Follow
Jul 11
Vulkan Computing with FP16 on PS4 GPU
#
ai
#
programming
#
vulkan
#
gpu
Comments
Add Comment
1 min read
Running Multiple ComfyUI Instances in Parallel on a Single GPU — What Actually Breaks First
Abdollah Ebadi
Abdollah Ebadi
Abdollah Ebadi
Follow
Jul 11
Running Multiple ComfyUI Instances in Parallel on a Single GPU — What Actually Breaks First
#
comfyui
#
python
#
machinelearning
#
gpu
Comments
Add Comment
14 min read
Linux 7.2 Improves Multi-GPU Displays, M3 Support, Mesa Rusticl Defaults Arm Mali
soy
soy
soy
Follow
Jul 11
Linux 7.2 Improves Multi-GPU Displays, M3 Support, Mesa Rusticl Defaults Arm Mali
#
gpu
#
nvidia
#
hardware
Comments
Add Comment
3 min read
Does a Second GPU Increase Ollama's Context Window? (Quadro P2000 + RTX 3090 Tested)
Arsen Apostolov
Arsen Apostolov
Arsen Apostolov
Follow
Jul 9
Does a Second GPU Increase Ollama's Context Window? (Quadro P2000 + RTX 3090 Tested)
#
llm
#
ollama
#
vllm
#
gpu
Comments
Add Comment
3 min read
LLM Inference Latency: Why Your 7B Model Gets 15 tok/s on a T4 but 3,500 tok/s on an H100
Rey Kingers
Rey Kingers
Rey Kingers
Follow
Jul 13
LLM Inference Latency: Why Your 7B Model Gets 15 tok/s on a T4 but 3,500 tok/s on an H100
#
ai
#
gpu
#
machinelearning
#
programming
2
 reactions
Comments
1
 comment
5 min read
Bitluni's 8,192-Core DIY GPU Is Built From 13-Cent RISC-V Chips
circuitrocks
circuitrocks
circuitrocks
Follow
Jul 8
Bitluni's 8,192-Core DIY GPU Is Built From 13-Cent RISC-V Chips
#
riscv
#
microcontrollers
#
gpu
#
pcbdesign
Comments
Add Comment
2 min read
CPU vs GPU: Why Large Language Models Need GPUs — What Really Happens After You Press Enter?
uttesh
uttesh
uttesh
Follow
Jul 8
CPU vs GPU: Why Large Language Models Need GPUs — What Really Happens After You Press Enter?
#
ai
#
llm
#
gpu
#
beginners
1
 reaction
Comments
Add Comment
4 min read
The KV cache, why LLM inference is memory-bound, not compute-bound
I Want To Learn Programming
I Want To Learn Programming
I Want To Learn Programming
Follow
Jul 4
The KV cache, why LLM inference is memory-bound, not compute-bound
#
gpu
#
llm
#
inference
#
performance
Comments
Add Comment
4 min read
The GPU Utilization Number That's Quietly Wrecking AI Team Budgets
Mike Smith
Mike Smith
Mike Smith
Follow
for
Hostrunway
Jul 3
The GPU Utilization Number That's Quietly Wrecking AI Team Budgets
#
gpu
#
ai
#
machinelearning
#
deeplearning
Comments
Add Comment
5 min read
DGX Spark hitting 83 C under sustained Ollama load — solved by clock-locking via nvidia-smi -lgc
Deal Estate
Deal Estate
Deal Estate
Follow
Jul 1
DGX Spark hitting 83 C under sustained Ollama load — solved by clock-locking via nvidia-smi -lgc
#
nvidia
#
gpu
#
llm
#
ai
Comments
Add Comment
3 min read
Resurrecting Kepler: Getting Modern LLMs Running on a GTX 770 (Kernel 7.x)
skyne
skyne
skyne
Follow
Jun 27
Resurrecting Kepler: Getting Modern LLMs Running on a GTX 770 (Kernel 7.x)
#
cuda
#
linux
#
llm
#
gpu
1
 reaction
Comments
Add Comment
4 min read
Per-agent GPU cost: what LangSmith can't tell you
David AMARA
David AMARA
David AMARA
Follow
Jun 28
Per-agent GPU cost: what LangSmith can't tell you
#
ai
#
gpu
#
finops
#
llm
Comments
1
 comment
4 min read
Managing Non-Homogeneous GPU and Resource Configurations in Ray Cluster IaC with Python-Based Solutions
Marina Kovalchuk
Marina Kovalchuk
Marina Kovalchuk
Follow
Jun 28
Managing Non-Homogeneous GPU and Resource Configurations in Ray Cluster IaC with Python-Based Solutions
#
raycluster
#
iac
#
python
#
gpu
Comments
Add Comment
15 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