Skip to content

Issues: NVIDIA/FasterTransformer

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

Clear current search query, filters, and sorts
249 Open 376 Closed
249 Open 376 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

error: ‘CUDNN_DATA_BFLOAT16’ was not declared in this scope; did you mean ‘CUDNN_DATA_FLOAT’
#789 by johnson-magic was closed Mar 29, 2024
multi_block_mode performance issue
#782 by akhoroshev was closed Dec 6, 2023
1
repetition_penalty logic in FT has bug bug Something isn't working
#777 by hezeli123 was closed Nov 2, 2023
1
How to serving multi-gpu inference？
#772 by Alone-wl was closed Dec 21, 2023
1
How to run multi_gpu_gpt_examples.py without mpirun/mpiexe
#747 by ZZWHU was closed Aug 30, 2023
Which version of cutlass was adopted？
#723 by Liu-xiandong was closed Jul 18, 2023
I tried your way, but still get this error
#721 by pangr was closed Jul 17, 2023
docker/Dockerfile.torch occurs errors bug Something isn't working
#720 by b3y0nd was closed Sep 21, 2023
4
Incomplete explanation bug Something isn't working
#719 by lix19937 was closed Jul 15, 2023
1
GPTNeox decoding argumentation
#712 by w775739733 was closed Jul 11, 2023
opt-6.7b smoothquant result error bug Something isn't working
#709 by sitabulaixizawaluduo was closed Jul 10, 2023
cuda 11.7 and cuda 11.8 gives different results for decoder self-attention?
#702 by frankxyy was closed Jul 17, 2023
[Compile] Compilation Failed when CMake using CUDA 11.8 on Windows. bug Something isn't working
#688 by FdyCN was closed Jun 28, 2023
3
ParallelGPT stop_words_list bug Something isn't working
#677 by cpm0722 was closed Jul 17, 2023
[bug] CustomAllReduceComm swapInternalBuffer is not safe (modifying const pointer). bug Something isn't working
#671 by rkindi was closed Jul 6, 2023
5
# Feature Request # Multi Query Attention (MQA) supprot request
#668 by Xingxiangrui was closed Aug 21, 2023
10
[soft prompt] llama generation quality decrease when using soft prompt
#661 by handoku was closed Jun 11, 2023
1
mt5-small accuracy issue bug Something isn't working
#654 by ashleyLtj was closed Jun 12, 2023
can't find lib/libth_transformer.so
#650 by Wanan-ni was closed Jun 5, 2023
It seems not support cudagraph ? bug Something isn't working
#637 by lix19937 was closed Jul 7, 2023
1
It seems not support cudagraph ? bug Something isn't working
#636 by lix19937 was closed May 29, 2023
1
The model processed by SFT infers garbled results on the FasterTransformer backend bug Something isn't working
#635 by WackyGem was closed May 27, 2023
1
The model processed by SFT infers garbled results on the FasterTransformer backend bug Something isn't working
#634 by WackyGem was closed Sep 15, 2023
12
GptNeoX fails to stop inference when encountering end_id
#631 by SeibertronSS was closed May 23, 2023
2
GptNeoX fails to stop inference when encountering end_id bug Something isn't working
#630 by SeibertronSS was closed May 23, 2023
ProTip! Updated in the last three days: updated:>2025-01-16.