Skip to content

Conversation

@b4rtaz
Copy link
Owner

@b4rtaz b4rtaz commented Aug 13, 2025

Model: llama3_1_8b_instruct_q40.
GPU: NVIDIA GeForce RTX 3060 12 GB

Prediction

  • before: 14.87 tok/s
  • this PR: 16.01 tok/s

@b4rtaz b4rtaz merged commit eda0684 into main Aug 13, 2025
3 checks passed
@b4rtaz b4rtaz deleted the feat/vulkan-barriers-2 branch August 18, 2025 11:53
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