riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 23 Packages Projects Releases Wiki Activity

Quantization / TST: Fix remaining quantization tests (#31000)

Browse Source 
* Fix remaining quant tests

* Update test_quanto.py
This commit is contained in:
Younes Belkada 2024-05-24 14:35:59 +02:00 committed by GitHub
parent fd3c128040
commit 658b849aeb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docker/transformers-all-latest-gpu/Dockerfile
View File

@ -45,9 +45,6 @@ RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/opt
# For video model testing
RUN python3 -m pip install --no-cache-dir decord av==9.2.0
# For GGUF tests
RUN python3 -m pip install --no-cache-dir gguf
# Some slow tests require bnb
RUN python3 -m pip install --no-cache-dir bitsandbytes

3
docker/transformers-quantization-latest-gpu/Dockerfile
View File

@ -48,6 +48,9 @@ RUN python3 -m pip install --no-cache-dir aqlm[gpu]==1.0.2
# Add hqq for quantization testing
RUN python3 -m pip install --no-cache-dir hqq
# For GGUF tests
RUN python3 -m pip install --no-cache-dir gguf
# Add autoawq for quantization testing
# >=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

3
tests/quantization/quanto_integration/test_quanto.py
View File

@ -440,6 +440,7 @@ class QuantoQuantizationActivationTest(unittest.TestCase):
self.assertIn("We don't support quantizing the activations with transformers library", str(e.exception))
@require_quanto
@require_torch_gpu
class QuantoKVCacheQuantizationTest(unittest.TestCase):
@slow
@ -447,7 +448,7 @@ class QuantoKVCacheQuantizationTest(unittest.TestCase):
def test_quantized_cache(self):
EXPECTED_TEXT_COMPLETION = [
"Simply put, the theory of relativity states that 1) the speed of light is the same for all observers, and 2) the laws of physics are the same for all observers.\nThe first part of the theory of relativity",
"My favorite all time favorite condiment is ketchup. I love it on everything. I love it on my eggs, my fries, my burgers, my hot dogs, my sandwiches, my chicken, my pizza, my sal",
"My favorite all time favorite condiment is ketchup. I love it on everything. I love it on my eggs, my fries, my burgers, my hot dogs, my sandwiches, my salads, my chicken, my fish",
]
prompts = [