• Hi Guest!

    We are extremely excited to announce the release of our first Beta1.1 and the first release of our Public AddonKit!
    To participate in the Beta, a subscription to the Entertainer or Creator Tier is required. For access to the Public AddonKit you must be a Creator tier member. Once subscribed, download instructions can be found here.

    Click here for information and guides regarding the VaM2 beta. Join our Discord server for more announcements and community discussion about VaM2.
  • Hi Guest!

    VaM2 Resource Categories have now been added to the Hub! For information on posting VaM2 resources and details about VaM2 related changes to our Community Forums, please see our official announcement here.
CPU Performance Patch (Up to 30% faster physics, up to 60% more FPS)

Plugins + Scripts CPU Performance Patch (Up to 30% faster physics, up to 60% more FPS)

Download [1.97 MB]
but is the creator of this optimization plugin still alive? or is he dead?

why am I asking this? simple because I wrote the previous message to know how the plugin works and no one answered me, so I wrote a similar message in private to turtlebackgoofy and he still doesn't answer me so I would like to understand if this person does it on purpose not to answer the questions or if he is dead and therefore that's why he doesn't answer?
I need to know how to set up the plugin for my computer, I can't risk burn it for these things.
I add that if there was also my current model which would be AMD Ryzen 5600G, I wouldn't have even written, but since there is a 5600x I checked and they are different so I don't know if I can use the same settings as the 5600x with the 5600g.
Maybe he is busy with real life stuff.
 
I made some tests and what I got. I have 6 cpu cores and 12 logical cores. Can I make it better or this settings are fine?

Code:
[threads]
computeColliders=6
skinmeshPart=6
skinmeshPartMaxPerChar=6
applyMorphs=6
applyMorphMaxPerChar=6
affinity=1,3,5,7,9,11
engineAffinity=1,3
 

Attachments

  • Benchmark-20250627-191826.png
    Benchmark-20250627-191826.png
    844.8 KB · Views: 0
  • Benchmark-20250627-193359.png
    Benchmark-20250627-193359.png
    846.6 KB · Views: 0
AMD 2700X and zero improvements. Shift deleted this. Maybe with the 9800X3D when I get a job..

Allright upgraded to the 5700X3D and this thing is a beast.
 
Last edited:
I made some tests and what I got. I have 6 cpu cores and 12 logical cores. Can I make it better or this settings are fine?

Code:
[threads]
computeColliders=6
skinmeshPart=6
skinmeshPartMaxPerChar=6
applyMorphs=6
applyMorphMaxPerChar=6
affinity=1,3,5,7,9,11
engineAffinity=1,3
Thats excellent! 60-90% uplift. Looks thats the best you can do for settings. Now the gpu is the bottleneck.
 
What settings for the performance patches and config file are suppose to be used for a Ryzen 9900x
 
After I did this patch update. I have had my PC shutdown on me twice while I was on vam. Thinking about reverting back to original to see if this was truly the cause of it. How should I do so.
 
After I did this patch update. I have had my PC shutdown on me twice while I was on vam. Thinking about reverting back to original to see if this was truly the cause of it. How should I do so.
Probably means you set your ini settings too high, I did that and also had computer crash issues.
 
tip for anyone here looking to match settings to CPU, ChatGPT can now suggest settings tailored to your CPU. Here's what I asked it:

in skinmeshpart.dll for Virt-A-Mate, I have the following settings:
[threadsVR]
computeColliders=8s
kinmeshPart=8
skinmeshPartMaxPerChar=6
applyMorphs=8
applyMorphMaxPerChar=6
#affinity=0,2,4,6,8,10,12,14

Which settings are most appropriate for an Intel i-9 9900k?

GhatGPT:
Here’s the config I’d recommend:

[threadsVR]
computeColliders=8
skinmeshPart=8
skinmeshPartMaxPerChar=3
applyMorphs=8
applyMorphMaxPerChar=3
#affinity=0,2,4,6,8,10,12,14

Why this is the “heavy 2-char safe” setup​


  • computeColliders=8 → full use of your 8 physical cores for collision physics, which is usually the biggest CPU load in VaM.
  • skinmeshPart=8 / applyMorphs=8 → plenty of worker threads in the pool, so both characters can run in parallel.
  • MaxPerChar=3→ keeps each character capped at 3 threads for morphs + 3 for skinmesh.
    • 2 characters × 3 = 6 threads each → 12 threads total across morph + mesh.
    • This stays comfortably within your 8 physical cores, with some spillover into SMT but not overload.
  • Affinity left commented → Windows can spread workload as needed. Only enable if you notice inconsistent thread usage or cache thrash.

Tried it and I do seem to be getting better performance! Who would have thought ChatGPT would know about vam
 
Last edited:
Back
Top Bottom