issues
search
huggingface
/
optimum-neuron
Easy, fast and very cheap training and inference on AWS Trainium and Inferentia chips.
Apache License 2.0
176
stars
51
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
nvidia/Llama3-ChatQA-1.5-70B failing to start
#596
mariokostelac
opened
1 month ago
10
Fix excessive CPU memory consumption on TGI startup
#595
dacorvo
closed
1 month ago
0
Fix diffusion caching
#594
oOraph
closed
1 month ago
2
caching diffusion models does not work
#593
oOraph
closed
1 month ago
3
enable unequal height and width
#592
yahavb
closed
1 month ago
3
Bump dev version
#591
JingyaHuang
closed
1 month ago
1
Change inline weights to Neff default value to True
#590
JingyaHuang
closed
1 month ago
1
Improve tgi env wrapper for neuron
#589
oOraph
closed
1 month ago
0
Separate sections for tutorials
#588
michaelbenayoun
opened
1 month ago
2
Improve llama models performance
#587
dacorvo
closed
1 month ago
2
Deprecate resume_download
#586
Wauplin
closed
3 weeks ago
4
Ease the tests when there is no hf token
#585
JingyaHuang
closed
1 month ago
0
[Inference] Fix inference latency issue when weights/neff are separated
#584
JingyaHuang
closed
1 month ago
1
[Inference] Add `SentenceTransformers` support to `pipeline` for `feature-extration`
#583
philschmid
closed
1 month ago
2
Add guide for LoRA adapters
#582
JingyaHuang
closed
2 months ago
1
Make stable diffusion pipelines compatible with compel
#581
JingyaHuang
closed
2 months ago
3
eos_token_id can be a list in configs
#580
dacorvo
closed
2 months ago
1
optimum-cli neuron consolidate -> OOM. Using only one Neuron Core
#579
MarcoBFreitas
opened
2 months ago
2
Fixes `test_examples.py` tests collection
#578
michaelbenayoun
opened
2 months ago
4
Update TGI router version to 2.0.1
#577
dacorvo
closed
2 months ago
0
Poor performance to generate images with NeuronStableDiffusionPipeline
#576
yahavb
closed
2 months ago
3
Add optimum-neuron support for diffusers.StableDiffusionControlNetPipeline
#575
yahavb
closed
3 days ago
3
missing \ in quickstart inference guide
#574
yahavb
closed
2 months ago
1
Inf1: optimum neuron inference tests failing with import errors from transformers.utils and huggingface_hub
#573
musunita
closed
1 month ago
5
Use AWS 2.18.0 AMI as base
#572
dacorvo
closed
2 months ago
0
Optimum neuron inference test results with NotImplementedError.
#571
musunita
opened
2 months ago
4
fix(decoder): specify libraryname to suppress warning
#570
dacorvo
closed
2 months ago
1
Add support for Mixtral
#569
dacorvo
closed
2 months ago
1
Save checkpoint weights in safetensors format when exporting decoder models
#568
a-ys
closed
2 months ago
1
Do not split decoder checkpoint files
#567
dacorvo
closed
2 months ago
1
Allow download subfolder for caching models with subfolder
#566
JingyaHuang
closed
2 months ago
2
Skip weight splitting for SafeTensors Weights
#565
a-ys
opened
2 months ago
5
TGI benchmark with llmperf
#564
dacorvo
closed
2 months ago
0
Modify benchmarks
#563
dacorvo
closed
2 months ago
1
Sync `transformers` and `accelerate` versions
#562
michaelbenayoun
closed
1 month ago
3
Extend TGI integration tests
#561
dacorvo
closed
2 months ago
0
Integrate new API for saving and loading with `neuronx_distributed`
#560
michaelbenayoun
closed
2 months ago
2
Improve installation guide
#559
JingyaHuang
closed
2 months ago
1
chore: bump dev version
#558
JingyaHuang
closed
2 months ago
2
Update cache guide to including the caching for traced models
#557
JingyaHuang
opened
2 months ago
6
Add step closure instead of regular log
#556
michaelbenayoun
closed
1 month ago
3
Cleanup obsolete code
#555
michaelbenayoun
closed
2 months ago
1
Disable weights / neff separation of SDXL's UNET for neuron sdk 2.18
#554
JingyaHuang
closed
2 months ago
1
Cache utils related cleanup
#553
michaelbenayoun
closed
2 months ago
3
Remove print that should not be there
#552
michaelbenayoun
closed
2 months ago
1
- new notebook - TGI + SageMaker + Mistral
#551
samir-souza
opened
2 months ago
2
Audio models
#550
michaelbenayoun
opened
2 months ago
4
Adding CodeLlama-7B inference and compilation example notebook
#549
jimburtoft
closed
2 months ago
2
Upgrade Neuron SDK to 2.18.0 and TGI to 1.4.5 (fix)
#548
davidshtian
closed
2 months ago
2
Use AWS Neuron sdk 2.18
#547
dacorvo
closed
2 months ago
6
Previous
Next