SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Fix quantization tests (#29914)

Browse Source 
* revert back to torch 2.1.1

* run test

* switch to torch 2.2.1

* udapte dockerfile

* fix awq tests

* fix test

* run quanto tests

* update tests

* split quantization tests

* fix

* fix again

* final fix

* fix report artifact

* build docker again

* Revert "build docker again"

This reverts commit 399a5f9d9308da071d79034f238c719de0f3532e.

* debug

* revert

* style

* new notification system

* testing notfication

* rebuild docker

* fix_prev_ci_results

* typo

* remove warning

* fix typo

* fix artifact name

* debug

* issue fixed

* debug again

* fix

* fix time

* test notif with faling test

* typo

* issues again

* final fix ?

* run all quantization tests again

* remove name to clear space

* revert modfiication done on workflow

* fix

* build docker

* build only quant docker

* fix quantization ci

* fix

* fix report

* better quantization_matrix

* add print

* revert to the basic one
This commit is contained in:
Marc Sun
2024-04-09 17:10:29 +02:00
committed by GitHub
parent 6487e9b370
commit 58a939c6b7
7 changed files with 324 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docker/transformers-quantization-latest-gpu/Dockerfile
View File

@@ -9,7 +9,7 @@ SHELL ["sh", "-lc"]
# The following `ARG` are mainly used to specify the versions explicitly & directly in this docker file, and not meant
# to be used as arguments for docker build (so far).
ARG PYTORCH='2.2.0'
ARG PYTORCH='2.2.1'
# Example: `cu102`, `cu113`, etc.
ARG CUDA='cu118'
@@ -30,6 +30,9 @@ RUN python3 -m pip install --no-cache-dir -e ./transformers[dev-torch]
RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/accelerate@main#egg=accelerate
# needed in bnb and awq
RUN python3 -m pip install --no-cache-dir einops
# Add bitsandbytes for mixed int8 testing
RUN python3 -m pip install --no-cache-dir bitsandbytes
@@ -43,7 +46,8 @@ RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/opt
RUN python3 -m pip install --no-cache-dir aqlm[gpu]==1.0.2
# Add autoawq for quantization testing
RUN python3 -m pip install --no-cache-dir https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.0/autoawq-0.2.0+cu118-cp38-cp38-linux_x86_64.whl
# >=v0.2.3 needed for compatibility with torch 2.2.1
RUN python3 -m pip install --no-cache-dir https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.3/autoawq-0.2.3+cu118-cp38-cp38-linux_x86_64.whl
# Add quanto for quantization testing
RUN python3 -m pip install --no-cache-dir quanto