Skip to content

Issues: huggingface/optimum-nvidia

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
50 Open 18 Closed
50 Open 18 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

Supporting Bert / Roberta - tags: enchancement / new_model model
#21 opened Dec 6, 2023 by michaelfeil
GPTQ support? enhancement New feature or request
#26 opened Dec 7, 2023 by tigerinus 0.1.0b3
@mfuntowicz
11
Excellent project, hopefully ChatGLM3 will be supported.
#33 opened Dec 10, 2023 by Jeru2023
Enhancing Compatibility and Extending Support for Optimum-NVIDIA Across Diverse Workloads
#34 opened Dec 11, 2023 by yihong1120
When is the pip install command coming?
#36 opened Dec 11, 2023 by BBC-Esq 0.1.0b3
2
roubleshooting installation issues with Optimum-NVIDIA without docker
#37 opened Dec 12, 2023 by arkaprovob 0.1.0b3
3
Segmentation fault: address not mapped to object at address 0xb1fe8
#44 opened Dec 14, 2023 by SinanAkkoyun
FileNotFoundError: [Errno 2] No such file or directory: '/data/Dilip/models/llama-2-7b-chat-hf/build.json' bug Something isn't working
#47 opened Dec 15, 2023 by dilip467
@mfuntowicz
8
Use FP8 by default when on a supported device
#50 opened Dec 15, 2023 by laikhtewari
@mfuntowicz
ImportError: Using low_cpu_mem_usage=True or a device_map requires Accelerate: pip install accelerate bug Something isn't working
#56 opened Dec 21, 2023 by taozhang9527 0.1.0b3
@mfuntowicz
RuntimeError: TRT Engine build failed...
#58 opened Dec 31, 2023 by yirunwang
1
Installation errors
#59 opened Jan 2, 2024 by RomanKoshkin
Feature request: streamer enhancement New feature or request
#60 opened Jan 2, 2024 by RomanKoshkin
Not able to run 'Generate' from QuickStart section bug Something isn't working
#61 opened Jan 3, 2024 by harikrishnaapc
@mfuntowicz
Pip Installation
#62 opened Jan 4, 2024 by rmccorm4
4
Build failed with cuda runtime error.
#64 opened Jan 8, 2024 by Anindyadeep
1
Mixtral support
#67 opened Jan 15, 2024 by nmiletic
4
Error when Running LLAMA with tensor parallelism = 2 bug Something isn't working
#68 opened Jan 23, 2024 by TheCodeWrangler
@mfuntowicz
1
Triton Inference Server
#69 opened Jan 23, 2024 by TheCodeWrangler
2
llama.py with fp8 is broken (inference produces garbage results)
#71 opened Feb 10, 2024 by urimerhav
3
How do you use the library in your scripts after pulling and running the Docker image?
#72 opened Feb 15, 2024 by jddunn
1
How to build this environment without docker?
#75 opened Feb 24, 2024 by lemon-little
1
Qwen Support
#84 opened Feb 28, 2024 by Yuchen-Cao
Incorrect tensorrt_llm config class initialization bug Something isn't working
#90 opened Mar 7, 2024 by Wojx
@mfuntowicz
Original model configuration (config.json) was not found error during running inference using "Llama-2-7b-chat-hf"
#91 opened Mar 8, 2024 by raorajendra
ProTip! Mix and match filters to narrow down what you’re looking for.