Skip to content

Add RTX 6000 speed#107

Open
d3y4n wants to merge 1 commit into
antirez:mainfrom
d3y4n:feature/speed-cuda
Open

Add RTX 6000 speed#107
d3y4n wants to merge 1 commit into
antirez:mainfrom
d3y4n:feature/speed-cuda

Conversation

@d3y4n
Copy link
Copy Markdown

@d3y4n d3y4n commented May 12, 2026

Based on the output of default benchmark cmd.

2048,2048,313.21,128,35.66,52184460
4096,2048,317.81,128,35.12,80373132
8192,2048,317.33,128,34.36,136750476
16384,2048,310.08,128,32.78,249505164
32768,2048,296.95,128,31.72,475014540
65536,2048,273.55,128,29.62,926033292

@tao12345666333
Copy link
Copy Markdown

Could you please share the complete operating steps and information about the machine resources?

This result differs significantly from the speed I tested.🤔

https://x.com/i/status/2054161265577308453

@d3y4n
Copy link
Copy Markdown
Author

d3y4n commented May 12, 2026

@tao12345666333 good callout, it did indeed look a bit suspicious, I'm running this on g7e.2xlarge AWS instance at the moment. I will the card in the upcoming weeks in my PC.

This is what I ran:

./ds4-bench \
  -m ds4flash.gguf \
  --prompt-file speed-bench/promessi_sposi.txt \
  --ctx-start 2048 \
  --ctx-max 65536 \
  --step-incr 2048 \
  --gen-tokens 128

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants