Skip to content

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.

Sign up for GitHub

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

127 Open 1,235 Closed
127 Open 1,235 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

"RuntimeError: weight lm_head.weight does not exist" quantizing Llama-3.2-11B-Vision-Instruct
#2775 opened Nov 22, 2024 by akowalsk
2 of 4 tasks
Latest Docker Image failing for A40 GPU
#2763 opened Nov 20, 2024 by SMAntony
2 of 4 tasks
The same model, but different loading methods will result in very different inference speeds?
#2757 opened Nov 19, 2024 by hjs2027864933
2 of 4 tasks
1
Regression in 2.4.0 : Input Valdidation errors return code 200 and do not return the error message
#2749 opened Nov 15, 2024 by leonarddls
2 of 4 tasks
On-The-Fly Quantization for Inference appears not to be working as per documentation.
#2748 opened Nov 15, 2024 by colin-byrneireland1
1 of 4 tasks
4
Different inference results and speed between /generate and OpenAI endpoint
#2747 opened Nov 14, 2024 by jegork
2 of 4 tasks
2
CUDA OutOfMemory even after warmup phase succeeded
#2744 opened Nov 13, 2024 by martinigoyanes
Support for Falcon-Mamba-7B
#2736 opened Nov 10, 2024 by mokeddembillel
1 of 2 tasks
1
In dev mode, server is stuck at Server started at unix:///tmp/text-generation-server-0
#2735 opened Nov 10, 2024 by mokeddembillel
2 of 4 tasks
Failed to build vllm in local install
#2734 opened Nov 9, 2024 by mokeddembillel
2 of 4 tasks
Bi-gram Repetation Penalty for the TGI configuration
#2731 opened Nov 7, 2024 by mertege
launch TGI with the argument --max-input-tokens smaller than sliding_window=4096 (got here max_input_tokens=16384)
#2730 opened Nov 7, 2024 by ashwincv0112
1 of 4 tasks
device-side assert triggered when trying to use LLaMA 3.2 Vision with grammar
#2729 opened Nov 6, 2024 by SokolAnn
2 of 4 tasks
TGI crashes while loading Qwen2-VL-7B-Instruct
#2728 opened Nov 6, 2024 by ktobah
2 of 4 tasks
1
Unable to load/run LoRA Adapters on llama - 7B
#2727 opened Nov 5, 2024 by kaushikmitr
Python client: Pydantic protected namespace "model_"
#2722 opened Nov 4, 2024 by Simon-Stone
4 tasks
FlashLlamaForCausalLM's using name dense for its mlp submodule causes error when using LoRA adapter
#2715 opened Nov 2, 2024 by sadra-barikbin
1
detokenize
#2705 opened Oct 29, 2024 by oroojlooy
CUDA Error: No kernel image is available for execution on the device
#2703 opened Oct 28, 2024 by shubhamgajbhiye1994
2 of 4 tasks
Is there a way to defines "bad_words"?
#2700 opened Oct 28, 2024 by tonylek
1
TGI Server should be installable via pip
#2696 opened Oct 27, 2024 by cdoern
Complexe response format lead the container to run forever on CPU
#2681 opened Oct 23, 2024 by Rictus
2 of 4 tasks
PREFIX_CACHING=0 does not disable prefix caching in v2.3.1
#2676 opened Oct 21, 2024 by sam-ulrich1
2 of 4 tasks
2
(Prefill) KV Cache Indexing error if started multiple TGI servers concurrently
#2675 opened Oct 21, 2024 by nathan-az
3 of 4 tasks
Prefix caching causes 2 different responses from the same HTTP call with seed set depending on what machine calls
#2670 opened Oct 18, 2024 by sam-ulrich1
2 of 4 tasks
5
ProTip! Follow long discussions with comments:>50.