-
Notifications
You must be signed in to change notification settings - Fork 1k
Issues: huggingface/text-generation-inference
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
TGI keeps referencing the default model in the image (bigscience/bloom)
#2534
opened Sep 18, 2024 by
BeylasanRuzaiqi
2 of 4 tasks
Support for returning a
CompletionUsage
object when streaming=True
#2531
opened Sep 17, 2024 by
andrewrreed
xpu/cpu: docker images referenced in documentation do not exist
#2530
opened Sep 17, 2024 by
dvrogozh
* HTTP 1.0, assume close after body < HTTP/1.0 503 Service Unavailable
#2526
opened Sep 17, 2024 by
aditivw
4 tasks
Add
response_format
input parameter to v1/chat/completions
endpoint
#2523
opened Sep 16, 2024 by
ktrapeznikov
tgi server launch fails with latest-rocm docker image.
#2522
opened Sep 13, 2024 by
gurpreet-dhami
3 of 4 tasks
RuntimeError: weight model.embed_tokens.weight does not exist
#2509
opened Sep 11, 2024 by
jayus71
3 of 4 tasks
Add support for Idefics 3
new model
Request for integration of new model
#2503
opened Sep 7, 2024 by
stelterlab
2 tasks done
A seeming typo in
text_generation_server/utils/adapters.py
#2483
opened Sep 2, 2024 by
sadra-barikbin
Quantization Failure with Bitsandbytes on SageMaker TGI Deployment: Compatibility Issue?
#2467
opened Aug 28, 2024 by
imadoualid
Could not import SGMV kernel from Punica, falling back to loop.
#2465
opened Aug 28, 2024 by
ksajan
2 of 4 tasks
Support Phi-3.5 MoE
new model
Request for integration of new model
#2457
opened Aug 25, 2024 by
maziyarpanahi
[Volta] [No flash attention] Dependencies missing for running quantized Llama models in docker
#2448
opened Aug 22, 2024 by
ladi-pomsar
2 of 4 tasks
Previous Next
ProTip!
Follow long discussions with comments:>50.