Hugo Larcher

hlarcher

AI & ML interests

None yet

Recent Activity

updated a model 11 days ago

hlarcher/opt-125m-lfs

published a model 11 days ago

hlarcher/opt-125m-lfs

updated a model 11 days ago

hlarcher/opt-125m

View all activity

Organizations

hlarcher's activity

updated a model 11 days ago

hlarcher/opt-125m-lfs

Text Generation • Updated 11 days ago • 3

published a model 11 days ago

hlarcher/opt-125m-lfs

Text Generation • Updated 11 days ago • 3

updated a model 11 days ago

hlarcher/opt-125m

Text Generation • Updated 11 days ago • 91

published a model 11 days ago

hlarcher/opt-125m

Text Generation • Updated 11 days ago • 91

updated a dataset 18 days ago

hlarcher/inference-benchmarker-xet

Updated 18 days ago • 51

published a dataset 18 days ago

hlarcher/inference-benchmarker-xet

Updated 18 days ago • 51

upvoted an article 18 days ago

Article

From Chunks to Blocks: Accelerating Uploads and Downloads on the Hub

20 days ago

• 49

authored a paper 26 days ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published 27 days ago • 197

upvoted an article about 1 month ago

Article

Welcome to Inference Providers on the Hub 🔥

Jan 28

• 404

posted an update about 2 months ago

Post

1077

We are introducing multi-backend support in Hugging Face Text Generation Inference!
With new TGI architecture we are now able to plug new modeling backends to get best performances according to selected model and available hardware. This first step will very soon be followed by the integration of new backends (TRT-LLM, llama.cpp, vLLM, Neuron and TPU).

We are polishing the TensorRT-LLM backend which achieves impressive performances on NVIDIA GPUs, stay tuned 🤗 !

Check out the details: https://huggingface.co/blog/tgi-multi-backend