huggingface optimum-nvidia issues

huggingface / optimum-nvidia

Apache License 2.0

867 stars 86 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Let's make sure to use the repeated heads tensor when in a non-mha scenario

#48 mfuntowicz closed 8 months ago
0
FileNotFoundError: [Errno 2] No such file or directory: '/data/Dilip/models/llama-2-7b-chat-hf/build.json'

#47 dilip467 opened 8 months ago
8
Use the new runtime handled allocation

#46 mfuntowicz closed 8 months ago
0
Enable testing on GPUs

#45 mfuntowicz closed 8 months ago
0
Segmentation fault: address not mapped to object at address 0xb1fe8

#44 SinanAkkoyun opened 8 months ago
0
Initial set of unittest in CI

#43 mfuntowicz closed 8 months ago
0
Mistral-7B

#42 rmccorm4 closed 8 months ago
13
Update to latest trtllm f7eca56161d496cbd28e8e7689dbd90003594bd2

#41 mfuntowicz closed 8 months ago
0
Fix typo

#40 mfuntowicz closed 8 months ago
0
Add initial set of documentation to build the `optimum-nvidia` container

#39 mfuntowicz closed 8 months ago
0
Build from source instructions

#38 laikhtewari closed 8 months ago
0
roubleshooting installation issues with Optimum-NVIDIA without docker

#37 arkaprovob opened 8 months ago
3
When is the pip install command coming?

#36 BBC-Esq opened 9 months ago
2
Enable more SM architectures in the prebuild docker

#35 mfuntowicz closed 8 months ago
1
Enhancing Compatibility and Extending Support for Optimum-NVIDIA Across Diverse Workloads

#34 yihong1120 opened 9 months ago
0
Excellent project, hopefully ChatGLM3 will be supported.

#33 Jeru2023 opened 9 months ago
0
Installation Error

#32 JamesKnight0001 closed 9 months ago
1
Update README.md

#31 eltociear closed 9 months ago
0
Quality

#30 mfuntowicz closed 8 months ago
0
Fix issue returning only the first batch item after pipeline call.

#29 mfuntowicz closed 9 months ago
0
Pipeline returns only the first item in a batch

#28 mfuntowicz closed 9 months ago
0
bump trt llm version to 0.6.1

#27 laikhtewari closed 9 months ago
0
GPTQ support?

#26 tigerinus opened 9 months ago
11
Fix syntax errors in setup.py

#25 tolgayan closed 9 months ago
1
AutoModelForCausalLM instead of LlamaForCausalLM

#24 laikhtewari closed 8 months ago
0
Error: cannot import name 'LlamaForCausalLM' from 'optimum.nvidia'

#23 taozhang9527 closed 8 months ago
4
Fix installation command

#22 laikhtewari closed 9 months ago
1
Supporting Bert / Roberta - tags: enchancement / new_model

#21 michaelfeil opened 9 months ago
0
FP8 Volta Architecture

#20 davide221 closed 9 months ago
1
Missing comma in setup.py

#19 IlyasMoutawwakil closed 9 months ago
0
Unable to build DockerFile

#18 bgagandeep closed 8 months ago
7
No kernel image is available for execution on the device

#17 Quang-elec44 closed 8 months ago
4
Fix wrong min instead of max when computing default max_new_tokens value

#16 mfuntowicz closed 9 months ago
0
Fix caching for docker

#15 mfuntowicz closed 8 months ago
0
Update docker to remove git lfs

#14 mfuntowicz closed 9 months ago
0
Bump version for release 0.1.0b1

#13 mfuntowicz closed 9 months ago
0
Readme tweaks

#12 laikhtewari closed 9 months ago
0
Fix scaling for the token/s metric

#11 mfuntowicz closed 9 months ago
0
Add the latest from TRTLLM

#10 mfuntowicz closed 9 months ago
0
Fix scaling for throughput

#9 laikhtewari closed 9 months ago
0
Create test.yml

#8 glegendre01 closed 9 months ago
0
Benchmarks

#7 mfuntowicz closed 9 months ago
0
MSL default in model config

#6 laikhtewari closed 9 months ago
2
Add TextGeneration pipeline

#5 mfuntowicz closed 9 months ago
0
Add `from_pretrained` and `save_pretrained` utilities to interact witth the hub

#4 mfuntowicz closed 9 months ago
0
update readme

#3 laikhtewari closed 9 months ago
0
Update TRTLLM to latest main version.

#2 mfuntowicz closed 9 months ago
0
Add LLama export capabilities

#1 mfuntowicz closed 9 months ago
0