-
Notifications
You must be signed in to change notification settings - Fork 1.2k
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
decoder_input_details and return_full_text parameters stopped providing previous log probs
#3070
opened Mar 4, 2025 by
sioan
4 tasks
Llama 3.3 70B Weird , gibberish outputs in production setup
#3043
opened Feb 20, 2025 by
andresC98
2 of 4 tasks
TGI metrics don't have model_name label to indicate which model the metrics belong to
#3026
opened Feb 17, 2025 by
yashaswipiplani
NIX: text_generation_launcher::gpu: Cannot determine GPU compute capability: ImportError: libffi.so.8
#3025
opened Feb 14, 2025 by
celsowm
1 of 4 tasks
WARN text_generation_launcher: Unkown compute for card nvidia-geforce-rtx-3090
#3014
opened Feb 11, 2025 by
bmilesp
Resource underutilization, thread thrashing: CPU affinity ignores allowed CPUs and cannot be switched off
#3011
opened Feb 11, 2025 by
askervin
3 of 4 tasks
Nonsense responses with n-gram speculative decoding
#2997
opened Feb 6, 2025 by
olliestanley
1 of 4 tasks
Request failed during generation: Server error: Value out of range: -29146814772
#2994
opened Feb 5, 2025 by
AlperYildirim1
2 of 4 tasks
Mistral Small 3 : chat template with python functions causes error
#2987
opened Feb 3, 2025 by
v3ss0n
2 tasks done
no prefill when decoder_input_details=True from InferenceClient
#2973
opened Jan 30, 2025 by
lifeng-jin
2 of 4 tasks
Incorrect Tokenization Likely Because of Diacritics in OpenChat and LLaMA 3.2 (TGI v3.0.2 and v2.2.0)
#2969
opened Jan 30, 2025 by
biba10
2 of 4 tasks
Structured output doesn't work with open ai endpoint
#2959
opened Jan 27, 2025 by
Stealthwriter
2 of 4 tasks
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.