Mark Kurtz

markurtz's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

commented a paper 22 days ago

"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization

Paper • 2411.02355 • Published 23 days ago • 45 •

3

authored 4 papers 22 days ago

How Well Do Sparse Imagenet Models Transfer?

Paper • 2111.13445 • Published Nov 26, 2021 • 1

The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models

Paper • 2203.07259 • Published Mar 14, 2022 • 3

Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment

Paper • 2405.03594 • Published May 6 • 7

"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization

Paper • 2411.02355 • Published 23 days ago • 45

upvoted a paper 23 days ago

"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization

Paper • 2411.02355 • Published 23 days ago • 45

New activity in neuralmagic/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic about 1 month ago

Can you please add Nemotron 70B static?

3

#1 opened about 1 month ago by nickandbro

updated a collection 3 months ago

Compressed LLMs from the Community

Collection

LLMs optimized by the community using Neural Magic's LLM Compressor for efficient deployment in vLLM. Contribute and help advance efficient AI! • 3 items • Updated Sep 26 • 2

upvoted a collection 3 months ago

Compressed LLMs from the Community

Collection

LLMs optimized by the community using Neural Magic's LLM Compressor for efficient deployment in vLLM. Contribute and help advance efficient AI! • 3 items • Updated Sep 26 • 2

updated 2 collections 3 months ago

Compressed LLMs from the Community

Collection

LLMs optimized by the community using Neural Magic's LLM Compressor for efficient deployment in vLLM. Contribute and help advance efficient AI! • 3 items • Updated Sep 26 • 2

FP8 LLMs for vLLM

Collection

Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! • 44 items • Updated Oct 17 • 59

New activity in neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16 4 months ago

Language support

1

#1 opened 4 months ago by ashbo