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

[Feature request] Implement 8-bit GPT-J #5

Closed
pablogranolabar opened this issue Nov 13, 2022 · 0 comments · Fixed by #27
Closed

[Feature request] Implement 8-bit GPT-J #5

pablogranolabar opened this issue Nov 13, 2022 · 0 comments · Fixed by #27
Labels
enhancement New feature or request

Comments

@pablogranolabar
Copy link

Results in ~11Gb weights vs. 16Gb, implemented in PyTorch now as load_in_8bit=True:

https://huggingface.co/hivemind/gpt-j-6B-8bit
@ggerganov ggerganov added the enhancement New feature or request label Nov 14, 2022
@ggerganov ggerganov mentioned this issue Feb 26, 2023
Merged
8 tasks
@katsu560 katsu560 mentioned this issue Mar 18, 2023
Merged
CCLDArjun pushed a commit to CCLDArjun/ggml that referenced this issue Dec 18, 2023
@SlyEcho @YellowRoseCx
@ardfork @funnbot @Engininja2 @KerfuffleV2 @jammm @jdecourval
ROCm Port (ggml-org#1087)
6bbc598 
* use hipblas based on cublas
* Update Makefile for the Cuda kernels
* Expand arch list and make it overrideable
* Fix multi GPU on multiple amd architectures with rocblas_initialize() (ggml-org#5)
* add hipBLAS to README
* new build arg LLAMA_CUDA_MMQ_Y
* fix half2 decomposition
* Add intrinsics polyfills for AMD
* AMD assembly optimized __dp4a
* Allow overriding CC_TURING
* use "ROCm" instead of "CUDA"
* ignore all build dirs
* Add Dockerfiles
* fix llama-bench
* fix -nommq help for non CUDA/HIP

---------

Co-authored-by: YellowRoseCx <80486540+YellowRoseCx@users.noreply.github.com>
Co-authored-by: ardfork <134447697+ardfork@users.noreply.github.com>
Co-authored-by: funnbot <22226942+funnbot@users.noreply.github.com>
Co-authored-by: Engininja2 <139037756+Engininja2@users.noreply.github.com>
Co-authored-by: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com>
Co-authored-by: jammm <2500920+jammm@users.noreply.github.com>
Co-authored-by: jdecourval <7315817+jdecourval@users.noreply.github.com>
PABannier added a commit to PABannier/ggml that referenced this issue Oct 20, 2024
@PABannier
sync: add ggml as submodule (ggml-org#5)
94775ca
eddierichter-amd pushed a commit to eddierichter-amd/ggml that referenced this issue Feb 17, 2025
@ypapadop-amd
Memory pool information and buffer allocation support (ggml-org#5)
8bfd477 
* Identifying memory pools

* Support for buffer type alignment and max size

* Cache memory properties

* Comments

* Using fixed-width integrals

* Buffer allocation support
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

4-bit Integer quantisation ggml-org/ggml
2 participants
@ggerganov @pablogranolabar