Hugo Larcher

hlarcher

AI & ML interests

None yet

Recent Activity

updated a model about 19 hours ago

hlarcher/opt-125m-lfs

published a model about 19 hours ago

hlarcher/opt-125m-lfs

updated a model about 22 hours ago

hlarcher/opt-125m

View all activity

Organizations

hlarcher's activity

updated a model about 19 hours ago

hlarcher/opt-125m-lfs

Text Generation • Updated about 19 hours ago

published a model about 19 hours ago

hlarcher/opt-125m-lfs

Text Generation • Updated about 19 hours ago

updated a model about 22 hours ago

hlarcher/opt-125m

Text Generation • Updated about 22 hours ago

published a model about 22 hours ago

hlarcher/opt-125m

Text Generation • Updated about 22 hours ago

updated a dataset 8 days ago

hlarcher/inference-benchmarker-xet

Updated 8 days ago • 21

published a dataset 8 days ago

hlarcher/inference-benchmarker-xet

Updated 8 days ago • 21

upvoted an article 8 days ago

Article

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

10 days ago

• 48

authored a paper 16 days ago

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

Paper • 2502.02737 • Published 17 days ago • 188

upvoted an article 25 days ago

Article

Welcome to Inference Providers on the Hub 🔥

25 days ago

• 381

posted an update about 1 month ago

Post

1074

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