Skip to content

Issues: triton-inference-server/tensorrtllm_backend

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

276 Open 235 Closed
276 Open 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

import PIL on demand
#674 opened Jan 2, 2025 by ShuaiShao93
Whisper - Missing parameters for triton deployment using tensorrt_llm backend bug Something isn't working
#672 opened Jan 2, 2025 by eleapttn
2 of 4 tasks
problem: lora_weights data type
#671 opened Dec 25, 2024 by Alireza3242
Mllama example does not run properly for v0.15 when using the tensorrt_llm_bls endpoint
#669 opened Dec 24, 2024 by here4dadata
Inflight Batching not working with OpenAI-Compatible Frontend bug Something isn't working
#667 opened Dec 22, 2024 by frosk1
2 of 4 tasks
Inference VILA 3b
#666 opened Dec 22, 2024 by anhnhust
lora_cache_gpu_memory_fraction is not a good parameter
#665 opened Dec 22, 2024 by Alireza3242
1
triton server multi request dynamic_batching not work bug Something isn't working
#661 opened Dec 13, 2024 by kazyun
2 of 4 tasks
1
InternVL deploy
#660 opened Dec 13, 2024 by ChenJian7578
when the End to end workflow to run a Multimodal model Support for InternVL2?
#659 opened Dec 13, 2024 by ChenJian7578
llm performance metric
#657 opened Dec 11, 2024 by weibingo
Qwen2___5-0___5B-Instruct convert_checkpoint error bug Something isn't working
#656 opened Dec 10, 2024 by giftyang
2 of 4 tasks
1
disaggregated_serving_bls: CPU usage
#653 opened Dec 2, 2024 by gary-wjc
1
triton streaming is not working as expected bug Something isn't working
#651 opened Nov 25, 2024 by robosina
2 of 4 tasks
Qwen2-VL support
#648 opened Nov 20, 2024 by zrczrczrc
2
Stub process 'whisper_bls_0_0' is not healthy. bug Something isn't working
#646 opened Nov 18, 2024 by MrD005
4 tasks
tensortllm backend fails when kv cache is disabled bug Something isn't working
#645 opened Nov 13, 2024 by ShuaiShao93
5
Support non-detached mode for python trtllm backend bug Something isn't working
#639 opened Nov 6, 2024 by ShuaiShao93
4 tasks
problem with output_log_probs need more info question Further information is requested
#632 opened Oct 28, 2024 by Alireza3242
@byshiue
3
the output of bls is unstable bug Something isn't working
#630 opened Oct 23, 2024 by dwq370
4 tasks
Streaming Inference Failure bug Something isn't working
#626 opened Oct 20, 2024 by imilli
2 of 4 tasks
1
The GPU memory usage is too high. bug Something isn't working
#625 opened Oct 19, 2024 by imilli
2 of 4 tasks
1
Garbage response when input tokens is longer than 4096 on Llama-3.1-8B-Instruct bug Something isn't working
#624 opened Oct 18, 2024 by winstxnhdw
2 of 4 tasks
2
Failed install in nvcr.io/nvidia/tritonserver:24.08-trtllm-python-py3 bug Something isn't working
#623 opened Oct 18, 2024 by wwx007121
4 tasks
Performance Issue with inflight_batcher_llm Model in v0.13.0
#622 opened Oct 18, 2024 by junstar92
6
ProTip! What’s not been updated in a month: updated:<2024-12-05.