Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Documentation] How to quantize using ggml? #320

Open
mahimairaja opened this issue Jun 28, 2023 · 0 comments
Open

[Documentation] How to quantize using ggml? #320

mahimairaja opened this issue Jun 28, 2023 · 0 comments

Comments

@mahimairaja
Copy link

Recently I found an awesome open-source LLM that has used ggml to quantize their model to 4-bit. I would love to learn more about similar practices. Any sort of blog, tutorial or documentation would be helpful.
CCLDArjun pushed a commit to CCLDArjun/ggml that referenced this issue Dec 18, 2023
@Ameobea
Add initial AVX512 support for dot product on Linux (ggerganov#320)
2e664f1 
 * Update Makefile to detect AVX512 support and add compiler flags if it's available
 * Based on existing AVX2 implementation, dot product on one 32-value block of 4-bit quantized ints at a time
 * Perform 8 bit -> 16 bit sign extension and multiply+add on 32 values at time instead of 16
 * Use built-in AVX512 horizontal reduce add to get sum at the end
 * Manual unrolling on inner dot product loop to reduce loop counter overhead
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@mahimairaja