Pruna 0.3.2: More OSS Algos, More Ways to Optimize
โข 5
AI & ML interests
Efficient machine learning for any model and hardware: pruning, quantization, compilation, and more.
Recent Activity
View all activity
Articles
update-format
#2 opened 3 days ago
by 
sdiazlor
README: license section and dataset citations
1
#11 opened 4 days ago
by 
begumcig
README: license section and dataset citations
1
#11 opened 4 days ago
by begumcig
sdiazlorย
updated a
Space 4 days ago
studio with gradio server and workflow
#1 opened 6 days ago
by 
akhaliq
nifleischย
published 2
models 6 days ago
nifleischย
published a
Space 6 days ago
update-for-launch
#1 opened 7 days ago
by sdiazlor
nifleischย
updated a
model 6 days ago
update-for-launch
#1 opened 7 days ago
by sdiazlor
Post
104
Hey! We published a set of 6-step LoRAs, one without the upsampling step: PrunaAI/P-Q-Image-2.1
- Generate or edit images in just 6 steps instead of 40. Use 6-steps for preserving inputs when editing and 6-steps-upsampled for improved visual quality and shorter end-to-end generation.
- 6-step distillation provides improved quality with few generation steps. 6-steps-upsampled is the first distillation that removes the need for a separate prompt-upsampling step. This means 41 to 80 seconds saved, depending on your prompt style.
- The LoRA adapters load directly on top of Qwen-Image-2.1, so the pipeline stays unchanged. Few-step distillation cuts the diffusion cost, and the upsampled adapter also removes the prompt-upsampling step before image generation.
- Generate or edit images in just 6 steps instead of 40. Use 6-steps for preserving inputs when editing and 6-steps-upsampled for improved visual quality and shorter end-to-end generation.
- 6-step distillation provides improved quality with few generation steps. 6-steps-upsampled is the first distillation that removes the need for a separate prompt-upsampling step. This means 41 to 80 seconds saved, depending on your prompt style.
- The LoRA adapters load directly on top of Qwen-Image-2.1, so the pipeline stays unchanged. Few-step distillation cuts the diffusion cost, and the upsampled adapter also removes the prompt-upsampling step before image generation.
Post
135
Hi! We open-source PrunaSuperPoint in collaboration with Eclipse Aidge for the DeepGreen project
It's an optimized version of SuperPoint built for faster keypoint detection on edge devices.
- Up to 2.1ร faster on Jetson Orin Nano, with optimizations applicable to other runtimes.
- The distilled model retains strong keypoint coverage across indoor and outdoor data, with low descriptor differences from the original model.
- We structurally prune the most expensive convolutional layers, recover performance through distillation, and accelerate keypoint selection with hierarchical top-k, all while preserving the original architectureโs core behavior.
Check it here: https://huggingface.co/PrunaAI/PrunaSuperPoint
It's an optimized version of SuperPoint built for faster keypoint detection on edge devices.
- Up to 2.1ร faster on Jetson Orin Nano, with optimizations applicable to other runtimes.
- The distilled model retains strong keypoint coverage across indoor and outdoor data, with low descriptor differences from the original model.
- We structurally prune the most expensive convolutional layers, recover performance through distillation, and accelerate keypoint selection with hierarchical top-k, all while preserving the original architectureโs core behavior.
Check it here: https://huggingface.co/PrunaAI/PrunaSuperPoint
Post
1,897
Today, we open-source Pruna-Qwen-Image-2.1, a set of a few-step LoRA adapters that make Qwen-Image-2. up to 6.3ร faster for image generation and editing.
Try it here: https://huggingface.co/PrunaAI/Pruna-Qwen-Image-2.1
Try it here: https://huggingface.co/PrunaAI/Pruna-Qwen-Image-2.1
Post
156
P-Bench: new public benchmark for T2I models
- Compare optimized or accelerated endpoints on quality, speed, and price.
- Analyze the paretos
- Explore the samples
Check it here ๐ PrunaAI/P-Bench
- Compare optimized or accelerated endpoints on quality, speed, and price.
- Analyze the paretos
- Explore the samples
Check it here ๐ PrunaAI/P-Bench
Post
169
Hey! We've released PrunaVAED, a drop-in replacement decoder for LTX-2.3
- ~1.7-2.1x faster decoder & ~50% lower peak VRAM
- Near-original visual quality & no changes to the latent encoding
Check it here: https://huggingface.co/PrunaAI/PrunaVAED
- ~1.7-2.1x faster decoder & ~50% lower peak VRAM
- Near-original visual quality & no changes to the latent encoding
Check it here: https://huggingface.co/PrunaAI/PrunaVAED
Post
203
As First Prune, the one-year Pruna OSS anniversary, is halfway.
Weโre sharing a recap blog post about our OSS journey โ how we started, what weโve built so far, and whatโs next.
Read it here: https://dev.to/pruna-ai/first-prune-celebrate-one-year-of-pruna-oss-50gp
Weโre sharing a recap blog post about our OSS journey โ how we started, what weโve built so far, and whatโs next.
Read it here: https://dev.to/pruna-ai/first-prune-celebrate-one-year-of-pruna-oss-50gp
Post
136
Pruna OSS is turning 1! To mark this milestone, we're launching the First Prune initiative.
What's First Prune:
If you contribute to open issues at our GitHub repo, you earn Pruna Inference API credits.
How you can participate:
โข Pick an open issue labelled "first-prune" and assign it to you
โข Submit your PR and mark it ready for review by April 30
โข Find out more in the PR template when you open a PR
Each merged PR scores 30 credits.
Letโs build something great together! Find your issue: https://github.com/PrunaAI/pruna/issues
What's First Prune:
If you contribute to open issues at our GitHub repo, you earn Pruna Inference API credits.
How you can participate:
โข Pick an open issue labelled "first-prune" and assign it to you
โข Submit your PR and mark it ready for review by April 30
โข Find out more in the PR template when you open a PR
Each merged PR scores 30 credits.
Letโs build something great together! Find your issue: https://github.com/PrunaAI/pruna/issues
Post
2,631
More OSS than ever with the latest pruna 0.3.2 release. It extends existing algorithm families, such as compilers, kernels, and pruners, and adds new ones, including decoders, distillers, enhancers, and recoverers. But it's not only a collection of algorithms; instead, you can easily combine them to get the biggest efficiency win.
Read the full blog here: https://huggingface.co/blog/PrunaAI/pruna-0-3-2-open-source-optimization-algorithms
Read the full blog here: https://huggingface.co/blog/PrunaAI/pruna-0-3-2-open-source-optimization-algorithms
davidberenstein1957ย
posted an update 11 months ago
Post
2,983
๐จ Phare LLM benchmark V2: Reasoning models don't guarantee better security
Read the full blog here: https://huggingface.co/blog/davidberenstein1957/phare-llm-benchmark-v2
Read the full blog here: https://huggingface.co/blog/davidberenstein1957/phare-llm-benchmark-v2