Disabling exllama on old compute. (#986)
# What does this PR do? Disabling exllama on old compute. Exllama + T4 don't play nice together, this will disable it right away to avoid issues at runtime. <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflects the extent of your awesome contribution. Then, please replace this with a description of the change and which issue is fixed (if applicable). Please also include relevant motivation and context. List any dependencies (if any) that are required for this change. Once you're done, someone will review your PR shortly (see the section "Who can review?" below to tag some potential reviewers). They may suggest changes to make the code even better. If no one reviewed your PR after a week has passed, don't hesitate to post a new comment @-mentioning the same persons---sometimes notifications get lost. --> <!-- Remove if not applicable --> Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. <!-- Your PR will be replied to more quickly if you can figure out the right person to tag with @ @OlivierDehaene OR @Narsil -->
This commit is contained in:
parent
3ed4c0f33f
commit
211e7b7e35
|
@ -18,13 +18,20 @@ from accelerate import init_empty_weights
|
|||
|
||||
from text_generation_server.utils.gptq.quant_linear import QuantLinear
|
||||
|
||||
HAS_EXLLAMA = True
|
||||
try:
|
||||
major, _minor = torch.cuda.get_device_capability()
|
||||
except Exception:
|
||||
major = 1
|
||||
HAS_EXLLAMA = False
|
||||
CAN_EXLLAMA = major >= 8
|
||||
if os.getenv("DISABLE_EXLLAMA") == "True":
|
||||
HAS_EXLLAMA = False
|
||||
try:
|
||||
from text_generation_server.utils.gptq.exllama import Ex4bitLinear
|
||||
except ImportError:
|
||||
HAS_EXLLAMA = False
|
||||
elif CAN_EXLLAMA:
|
||||
try:
|
||||
from text_generation_server.utils.gptq.exllama import Ex4bitLinear
|
||||
HAS_EXLLAMA = True
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
from typing import Optional
|
||||
|
||||
|
|
|
@ -170,10 +170,10 @@ class Weights:
|
|||
"Cannot load `gptq` weight, make sure the model is already quantized, or quantize it with `text-generation-server quantize ORIGINAL_MODEL_ID NEW_MODEL_ID`"
|
||||
)
|
||||
|
||||
from text_generation_server.utils.layers import HAS_EXLLAMA
|
||||
from text_generation_server.utils.layers import HAS_EXLLAMA, CAN_EXLLAMA
|
||||
|
||||
if use_exllama:
|
||||
if not HAS_EXLLAMA:
|
||||
if not HAS_EXLLAMA and CAN_EXLLAMA:
|
||||
logger.warning(
|
||||
"Exllama GPTQ cuda kernels (which are faster) could have been used, but are not currently installed, try using BUILD_EXTENSIONS=True"
|
||||
)
|
||||
|
|
Loading…
Reference in New Issue