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

114 Open 335 Closed
114 Open 335 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

GPU Kernel performance test with empty parameter without model load bug Something isn't working
#566 opened Apr 18, 2023 by 92hyungjun
3
Converting Flan-UL2 does not produce encoder files bug Something isn't working
#565 opened Apr 17, 2023 by anshoomehra
6
T5 MoE docs need updates
#562 opened Apr 17, 2023 by jokerwyt
2
convert nemo-megatron-mt5-3B to a binary file for triton-with-fastertransformer successfully, but tritonserver fails with undesired tensor shape when loading decoder.final_layernorm.bias.bin and shared.bias.bin.
#561 opened Apr 16, 2023 by songkq
8
CUDA out of memory in PyTorch OP
#560 opened Apr 14, 2023 by ZZBoom
3
How to use vit-Plugin Shared Libraries?
#559 opened Apr 14, 2023 by ywfwyht
Some examples do not appear to use ALIBI bias for models like BLOOM
#558 opened Apr 14, 2023 by abhi-mosaic
2
why I got error when "CMAKE_BUILD_TYPE=Debug"?
#557 opened Apr 13, 2023 by AkiyamaYummy
build error in cublasWrapper.cc bug Something isn't working
#556 opened Apr 13, 2023 by Jervint
9
[5.3.0] T5 model under FP16 is generating garbage bug Something isn't working
#554 opened Apr 12, 2023 by lanking520
2
Implementations of GPT/GPT-J/GPT-Neox
#553 opened Apr 12, 2023 by maltoak
4
How to infer on self-defined transformer structure?
#549 opened Apr 7, 2023 by frankxyy
1
some issues in the guide document
#548 opened Apr 7, 2023 by ZZBoom
1
The memory allocation for class Allocator<AllocatorType::CUDA> is very slow. bug Something isn't working
#547 opened Apr 7, 2023 by hongqing1986
2
GPT doesn't support sparsity?
#545 opened Apr 6, 2023 by chenrui17
1
Integer overflow with gpt_gemm bug Something isn't working
#544 opened Apr 5, 2023 by flx42
opt smoothquant model got runtime error when int8_mode=2 bug Something isn't working
#543 opened Apr 4, 2023 by fishelegs
4
Could NOT find MPI_CXX (missing: MPI_CXX_LIB_NAMES MPI_CXX_HEADER_DIR MPI_CXX_WORKS) bug Something isn't working
#542 opened Apr 4, 2023 by amazingkmy
1
GPT-NeoX HuggingFace Converter does not work bug Something isn't working
#540 opened Apr 3, 2023 by ankit-db
17
How to get single gpu gpt code?
#538 opened Apr 2, 2023 by yuxianzhi
3
How to do multi-node inference using docker
#534 opened Mar 31, 2023 by quwenjie
1
Can't get continue_gen to work with Python
#530 opened Mar 29, 2023 by ShaiMeital
1
sampling doesn't stop after words in stop_words_list are generated bug Something isn't working
#528 opened Mar 28, 2023 by shijie-wu
1
Stop the generation if the eod is reached
#526 opened Mar 28, 2023 by akhoroshev
3
The FT t5 beam search algorithm generates inconsistent results with HF's
#522 opened Mar 25, 2023 by shiqingzhangCSU
8
ProTip! Adding no:label will show everything without a label.