optimum-intel/transformers_daily_ci_intel_gaudi3
Updated
•
492
AI & ML interests
None defined yet.
Recent Activity
View all activity
hf-transformers-bot
updated
a
dataset
about 4 hours ago
IlyasMoutawwakil
posted
an
update
2 days ago
Post
2370
Transformers v5 just landed! 🚀
It significantly unifies and reduces modeling code across architectures, while opening the door to a whole new class of performance optimizations.
My favorite new feature? 🤔
The new dynamic weight loader + converter. Here’s why 👇
Over the last few months, the core Transformers maintainers built an incredibly fast weight loader, capable of converting tensors on the fly while loading them in parallel threads. This means we’re no longer constrained by how parameters are laid out inside the safetensors weight files.
In practice, this unlocks two big things:
- Much more modular modeling code. You can now clearly see how architectures build on top of each other (DeepSeek v2 → v3, Qwen v2 → v3 → MoE, etc.). This makes shared bottlenecks obvious and lets us optimize the right building blocks once, for all model families.
- Performance optimizations beyond what torch.compile can do alone. torch.compile operates on the computation graph, but it can’t change parameter layouts. With the new loader, we can restructure weights at load time: fusing MoE expert projections, merging attention QKV projections, and enabling more compute-dense kernels that simply weren’t possible before.
Personally, I'm honored to have contributed in this direction, including the work on optimizing MoE implementations and making modeling code more torch-exportable, so these optimizations can be ported cleanly across runtimes.
Overall, Transformers v5 is a strong signal of where the community and industry are converging: Modularity and Performance, without sacrificing Flexibility.
Transformers v5 makes its signature from_pretrained an entrypoint where you can mix and match:
- Parallelism
- Quantization
- Custom kernels
- Flash/Paged attention
- Continuous batching
- ...
Kudos to everyone involved! I highly recommend the:
Release notes: https://github.com/huggingface/transformers/releases/tag/v5.0.0
Blog post: https://huggingface.co/blog/transformers-v5
It significantly unifies and reduces modeling code across architectures, while opening the door to a whole new class of performance optimizations.
My favorite new feature? 🤔
The new dynamic weight loader + converter. Here’s why 👇
Over the last few months, the core Transformers maintainers built an incredibly fast weight loader, capable of converting tensors on the fly while loading them in parallel threads. This means we’re no longer constrained by how parameters are laid out inside the safetensors weight files.
In practice, this unlocks two big things:
- Much more modular modeling code. You can now clearly see how architectures build on top of each other (DeepSeek v2 → v3, Qwen v2 → v3 → MoE, etc.). This makes shared bottlenecks obvious and lets us optimize the right building blocks once, for all model families.
- Performance optimizations beyond what torch.compile can do alone. torch.compile operates on the computation graph, but it can’t change parameter layouts. With the new loader, we can restructure weights at load time: fusing MoE expert projections, merging attention QKV projections, and enabling more compute-dense kernels that simply weren’t possible before.
Personally, I'm honored to have contributed in this direction, including the work on optimizing MoE implementations and making modeling code more torch-exportable, so these optimizations can be ported cleanly across runtimes.
Overall, Transformers v5 is a strong signal of where the community and industry are converging: Modularity and Performance, without sacrificing Flexibility.
Transformers v5 makes its signature from_pretrained an entrypoint where you can mix and match:
- Parallelism
- Quantization
- Custom kernels
- Flash/Paged attention
- Continuous batching
- ...
Kudos to everyone involved! I highly recommend the:
Release notes: https://github.com/huggingface/transformers/releases/tag/v5.0.0
Blog post: https://huggingface.co/blog/transformers-v5
-
- 3 replies
IlyasMoutawwakil
posted
an
update
7 days ago
Post
2284
After 2 months of refinement, I'm happy to announce that a lot of Transformers' modeling code is now significantly more torch-compile & export-friendly 🔥
Why it had to be done 👇
PyTorch's Dynamo compiler is increasingly becoming the default interoperability layer for ML systems. Anything that relies on torch.export or torch.compile, from model optimization to cross-framework integrations, benefits directly when models can be captured as a single dynamo-traced graph !
Transformers models are now easier to:
⚙️ Compile end-to-end with torch.compile backends
📦 Export reliably via torch.export and torch.onnx.export
🚀 Deploy to ONNX / ONNX Runtime, Intel Corporation's OpenVINO, NVIDIA AutoDeploy (TRT-LLM), AMD's Quark, Meta's Executorch and more hardware-specific runtimes.
This work aims at unblocking entire TorchDynamo-based toolchains that rely on exporting Transformers across runtimes and accelerators.
We are doubling down on Transformers commitment to be a first-class citizen of the PyTorch ecosystem, more exportable, more optimizable, and easier to deploy everywhere.
There are definitely some edge-cases that we still haven't addressed so don't hesitate to try compiling / exporting your favorite transformers and to open issues / PRs.
PR in the comments ! More updates coming coming soon !
Why it had to be done 👇
PyTorch's Dynamo compiler is increasingly becoming the default interoperability layer for ML systems. Anything that relies on torch.export or torch.compile, from model optimization to cross-framework integrations, benefits directly when models can be captured as a single dynamo-traced graph !
Transformers models are now easier to:
⚙️ Compile end-to-end with torch.compile backends
📦 Export reliably via torch.export and torch.onnx.export
🚀 Deploy to ONNX / ONNX Runtime, Intel Corporation's OpenVINO, NVIDIA AutoDeploy (TRT-LLM), AMD's Quark, Meta's Executorch and more hardware-specific runtimes.
This work aims at unblocking entire TorchDynamo-based toolchains that rely on exporting Transformers across runtimes and accelerators.
We are doubling down on Transformers commitment to be a first-class citizen of the PyTorch ecosystem, more exportable, more optimizable, and easier to deploy everywhere.
There are definitely some edge-cases that we still haven't addressed so don't hesitate to try compiling / exporting your favorite transformers and to open issues / PRs.
PR in the comments ! More updates coming coming soon !
-
- 1 reply
jeffboudier
posted
an
update
5 months ago
Post
3154
Quick 30s demo of the new Hub > Azure AI integration to deploy HF models in your own Azure account. Now with Py and CLI!
GG @alvarobartt @kramp @pagezyhf
GG @alvarobartt @kramp @pagezyhf
IlyasMoutawwakil
posted
an
update
6 months ago
Post
3510
🚀 Optimum: The Last v1 Release 🚀
Optimum v1.27 marks the final major release in the v1 series. As we close this chapter, we're laying the groundwork for a more modular and community-driven future:
- Optimum v2: A lightweight core package for porting Transformers, Diffusers, or Sentence-Transformers to specialized AI hardware/software/accelerators..
- Optimum‑ONNX: A dedicated package where the ONNX/ONNX Runtime ecosystem lives and evolves, faster-moving and decoupled from the Optimum core.
🎯 Why this matters:
- A clearer governance path for ONNX, fostering stronger community collaboration and improved developer experience..
- Enable innovation at a faster pace in a more modular, open-source environment.
💡 What this means:
- More transparency, broader participation, and faster development driven by the community and key actors in the ONNX ecosystem (PyTorch, Microsoft, Joshua Lochner 👀, ...)
- A cleaner, more maintainable core Optimum, focused on extending HF libraries to special AI hardware/software/accelerators tooling and used by our partners (Intel Corporation, Amazon Web Services (AWS), AMD, NVIDIA, FuriosaAI, ...)
🛠️ Major updates I worked on in this release:
✅ Added support for Transformers v4.53 and SmolLM3 in ONNX/ONNXRuntime.
✅ Solved batched inference/generation for all supported decoder model architectures (LLMs).
✨ Big shoutout to @echarlaix for leading the refactoring work that cleanly separated ONNX exporter logic and enabled the creation of Optimum‑ONNX.
📝 Release Notes: https://lnkd.in/gXtE_qji
📦 Optimum : https://lnkd.in/ecAezNT6
🎁 Optimum-ONNX: https://lnkd.in/gzjyAjSi
#Optimum #ONNX #OpenSource #HuggingFace #Transformers #Diffusers
Optimum v1.27 marks the final major release in the v1 series. As we close this chapter, we're laying the groundwork for a more modular and community-driven future:
- Optimum v2: A lightweight core package for porting Transformers, Diffusers, or Sentence-Transformers to specialized AI hardware/software/accelerators..
- Optimum‑ONNX: A dedicated package where the ONNX/ONNX Runtime ecosystem lives and evolves, faster-moving and decoupled from the Optimum core.
🎯 Why this matters:
- A clearer governance path for ONNX, fostering stronger community collaboration and improved developer experience..
- Enable innovation at a faster pace in a more modular, open-source environment.
💡 What this means:
- More transparency, broader participation, and faster development driven by the community and key actors in the ONNX ecosystem (PyTorch, Microsoft, Joshua Lochner 👀, ...)
- A cleaner, more maintainable core Optimum, focused on extending HF libraries to special AI hardware/software/accelerators tooling and used by our partners (Intel Corporation, Amazon Web Services (AWS), AMD, NVIDIA, FuriosaAI, ...)
🛠️ Major updates I worked on in this release:
✅ Added support for Transformers v4.53 and SmolLM3 in ONNX/ONNXRuntime.
✅ Solved batched inference/generation for all supported decoder model architectures (LLMs).
✨ Big shoutout to @echarlaix for leading the refactoring work that cleanly separated ONNX exporter logic and enabled the creation of Optimum‑ONNX.
📝 Release Notes: https://lnkd.in/gXtE_qji
📦 Optimum : https://lnkd.in/ecAezNT6
🎁 Optimum-ONNX: https://lnkd.in/gzjyAjSi
#Optimum #ONNX #OpenSource #HuggingFace #Transformers #Diffusers
jeffboudier
posted
an
update
7 months ago
Post
572
AMD summer hackathons are here!
A chance to get hands-on with MI300X GPUs and accelerate models.
🇫🇷 Paris - Station F - July 5-6
🇮🇳 Mumbai - July 12-13
🇮🇳 Bengaluru - July 19-20
Hugging Face and GPU Mode will be on site and on July 6 in Paris @ror will share lessons learned while building new kernels to accelerate Llama 3.1 405B on ROCm
Register to Paris event: https://lu.ma/fmvdjmur?tk=KeAbiP
All dates: https://lu.ma/calendar/cal-3sxhD5FdxWsMDIz
A chance to get hands-on with MI300X GPUs and accelerate models.
🇫🇷 Paris - Station F - July 5-6
🇮🇳 Mumbai - July 12-13
🇮🇳 Bengaluru - July 19-20
Hugging Face and GPU Mode will be on site and on July 6 in Paris @ror will share lessons learned while building new kernels to accelerate Llama 3.1 405B on ROCm
Register to Paris event: https://lu.ma/fmvdjmur?tk=KeAbiP
All dates: https://lu.ma/calendar/cal-3sxhD5FdxWsMDIz
jeffboudier
posted
an
update
8 months ago
Post
1736
Today we launched Training Cluster as a Service, to make the new DGX Cloud Lepton supercloud easily accessible to AI researchers.
Hugging Face will collaborate with NVIDIA to provision and set up GPU training clusters to make them available for the duration of training runs.
Hugging Face organizations can sign up here: https://huggingface.co/training-cluster
Hugging Face will collaborate with NVIDIA to provision and set up GPU training clusters to make them available for the duration of training runs.
Hugging Face organizations can sign up here: https://huggingface.co/training-cluster
jeffboudier
posted
an
update
8 months ago
Post
2478
👏 Congrats
@jinanz
adding TimesFM times series forecasting to Transformers!
Learn how to use TimesFM in this blog post by the Nutanix team: https://huggingface.co/blog/Nutanix/introducing-timesfm-for-time-series-forcasting
Learn how to use TimesFM in this blog post by the Nutanix team: https://huggingface.co/blog/Nutanix/introducing-timesfm-for-time-series-forcasting
jeffboudier
posted
an
update
8 months ago
Post
504
Wrapping up a week of shipping and announcements with Dell Enterprise Hub now featuring AI Applications, on-device models for AI PCs, a new CLI and Python SDK... all you need for building AI on premises!
Blog post has all the details: https://huggingface.co/blog/dell-ai-applications
Blog post has all the details: https://huggingface.co/blog/dell-ai-applications
Post
2773
It will be very interesting to benchmark how energy-efficient the new Falcon-Edge is: https://huggingface.co/blog/tiiuae/falcon-edge
Should be super efficient on CPU according to the numbers published for BitNet: https://github.com/microsoft/BitNet/blob/main/assets/intel_performance.jpg
Should be super efficient on CPU according to the numbers published for BitNet: https://github.com/microsoft/BitNet/blob/main/assets/intel_performance.jpg
- 1 reply
jeffboudier
posted
an
update
9 months ago
Post
2615
Transcribing 1 hour of audio for less than $0.01 🤯
@mfuntowicz cooked with 8x faster Whisper speech recognition - whisper-large-v3-turbo transcribes at 100x real time on a $0.80/hr L4 GPU!
How they did it: https://huggingface.co/blog/fast-whisper-endpoints
1-click deploy with HF Inference Endpoints: https://huggingface.co/proxy/endpoints.huggingface.co/new?repository=openai%2Fwhisper-large-v3-turbo&vendor=aws®ion=us-east&accelerator=gpu&instance_id=aws-us-east-1-nvidia-l4-x1&task=automatic-speech-recognition&no_suggested_compute=true
@mfuntowicz cooked with 8x faster Whisper speech recognition - whisper-large-v3-turbo transcribes at 100x real time on a $0.80/hr L4 GPU!
How they did it: https://huggingface.co/blog/fast-whisper-endpoints
1-click deploy with HF Inference Endpoints: https://huggingface.co/proxy/endpoints.huggingface.co/new?repository=openai%2Fwhisper-large-v3-turbo&vendor=aws®ion=us-east&accelerator=gpu&instance_id=aws-us-east-1-nvidia-l4-x1&task=automatic-speech-recognition&no_suggested_compute=true
jeffboudier
posted
an
update
9 months ago
Post
3029
So many orgs on HF would really benefit from security and governance built into Enterprise Hub - I wrote a guide on why and how upgrade: https://huggingface.co/spaces/jeffboudier/how-to-upgrade-to-enterprise
For instance, did you know about Resource Groups?
For instance, did you know about Resource Groups?
jeffboudier
posted
an
update
10 months ago
Post
2216
Llama4 is out and Scout is already on the Dell Enterprise Hub to deploy on Dell systems 👉 dell.huggingface.co
jeffboudier
posted
an
update
10 months ago
Post
1589
Enterprise orgs now enable serverless Inference Providers for all members
- includes $2 free usage per org member (e.g. an Enterprise org with 1,000 members share $2,000 free credit each month)
- admins can set a monthly spend limit for the entire org
- works today with Together, fal, Novita, Cerebras and HF Inference.
Here's the doc to bill Inference Providers usage to your org: https://huggingface.co/docs/inference-providers/pricing#organization-billing
- includes $2 free usage per org member (e.g. an Enterprise org with 1,000 members share $2,000 free credit each month)
- admins can set a monthly spend limit for the entire org
- works today with Together, fal, Novita, Cerebras and HF Inference.
Here's the doc to bill Inference Providers usage to your org: https://huggingface.co/docs/inference-providers/pricing#organization-billing
- 2 replies
Post
1777
Nice paper comparing the fp8 inference efficiency of Nvidia H100 and Intel Gaudi2:
An Investigation of FP8 Across Accelerators for LLM Inference (2502.01070)
The conclusion is interesting: "Our findings highlight that the Gaudi 2, by leveraging FP8, achieves higher throughput-to-power efficiency during LLM inference"
One aspect of AI hardware accelerators that is often overlooked is how they consume less energy than GPUs. It's nice to see researchers starting carrying out experiments to measure this!
Gaudi3 results soon...
The conclusion is interesting: "Our findings highlight that the Gaudi 2, by leveraging FP8, achieves higher throughput-to-power efficiency during LLM inference"
One aspect of AI hardware accelerators that is often overlooked is how they consume less energy than GPUs. It's nice to see researchers starting carrying out experiments to measure this!
Gaudi3 results soon...
jeffboudier
posted
an
update
about 1 year ago
Post
758
NVIDIA just announced the Cosmos World Foundation Models, available on the Hub:
nvidia/cosmos-6751e884dc10e013a0a0d8e6
Cosmos is a family of pre-trained models purpose-built for generating physics-aware videos and world states to advance physical AI development.
The release includes Tokenizers nvidia/cosmos-tokenizer-672b93023add81b66a8ff8e6
Learn more in this great community article by @mingyuliutw and @PranjaliJoshi https://huggingface.co/blog/mingyuliutw/nvidia-cosmos
Cosmos is a family of pre-trained models purpose-built for generating physics-aware videos and world states to advance physical AI development.
The release includes Tokenizers nvidia/cosmos-tokenizer-672b93023add81b66a8ff8e6
Learn more in this great community article by @mingyuliutw and @PranjaliJoshi https://huggingface.co/blog/mingyuliutw/nvidia-cosmos
- 1 reply
Post
1043
Nice to see day 1 support of Falcon 3 on Gaudi with Optimum Habana!
👉 https://www.intel.com/content/www/us/en/developer/articles/technical/intel-ai-solutions-support-falcon-3-fdn-models.html
👉 https://www.intel.com/content/www/us/en/developer/articles/technical/intel-ai-solutions-support-falcon-3-fdn-models.html
jeffboudier
posted
an
update
about 1 year ago
Post
1147
New - add your bluesky account to your HF profile:
https://huggingface.co/settings/profile
Is the grass greener, the sky bluer? Will try and figure it out at https://bsky.app/profile/jeffboudier.bsky.social
By the way, HF people starter pack https://bsky.app/starter-pack/huggingface.bsky.social/3laz5x7naiz22
https://huggingface.co/settings/profile
Is the grass greener, the sky bluer? Will try and figure it out at https://bsky.app/profile/jeffboudier.bsky.social
By the way, HF people starter pack https://bsky.app/starter-pack/huggingface.bsky.social/3laz5x7naiz22
Post
1435
Interested in performing inference with an ONNX model?⚡️
The Optimum docs about model inference with ONNX Runtime is now much clearer and simpler!
You want to deploy your favorite model on the hub but you don't know how to export it to the ONNX format? You can do it in one line of code as follows:
Check out the whole guide 👉 https://huggingface.co/docs/optimum/onnxruntime/usage_guides/models
The Optimum docs about model inference with ONNX Runtime is now much clearer and simpler!
You want to deploy your favorite model on the hub but you don't know how to export it to the ONNX format? You can do it in one line of code as follows:
from optimum.onnxruntime import ORTModelForSequenceClassification
# Load the model from the hub and export it to the ONNX format
model_id = "distilbert-base-uncased-finetuned-sst-2-english"
model = ORTModelForSequenceClassification.from_pretrained(model_id, export=True)Check out the whole guide 👉 https://huggingface.co/docs/optimum/onnxruntime/usage_guides/models
jeffboudier
posted
an
update
over 1 year ago
Post
1123
This week in Inference Endpoints - thx
@erikkaum
for the update!
👀 https://huggingface.co/blog/erikkaum/endpoints-changelog
👀 https://huggingface.co/blog/erikkaum/endpoints-changelog
- 1 reply