Universal Assisted Generation: Faster Decoding with Any Assistant Model
ā¢
52
Joao Gante
joaogante
AI & ML interests
None yet
Recent Activity
upvoted
an
article
1 day ago
Welcome to Inference Providers on the Hub š„
upvoted
an
article
7 days ago
Mastering Long Contexts in LLMs with KVPress
liked
a model
8 days ago
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
Articles
Organizations
joaogante's activity
upvoted
an
article
1 day ago
Article
Welcome to Inference Providers on the Hub š„
ā¢
153
upvoted
an
article
7 days ago
Article
Mastering Long Contexts in LLMs with KVPress
By
ā¢
ā¢
56
upvoted
an
article
10 days ago
Article
Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference
ā¢
61
upvoted
2
articles
4 months ago
Article
Faster Assisted Generation with Dynamic Speculation
ā¢
44
Article
Improving Parquet Dedupe on Hugging Face Hub
ā¢
32
upvoted
2
articles
6 months ago
Article
XetHub is joining Hugging Face!
ā¢
81
Article
Google releases Gemma 2 2B, ShieldGemma and Gemma Scope
ā¢
59
upvoted
an
article
7 months ago
Article
Welcome Gemma 2 - Google's new open LLM
ā¢
126
upvoted
3
articles
8 months ago
Article
AI has a problem with objectifying women
By
ā¢
ā¢
55Article
From cloud to developers: Hugging Face and Microsoft Deepen Collaboration
ā¢
8
Article
Unlocking Longer Generation with Key-Value Cache Quantization
ā¢
40
upvoted
2
articles
9 months ago
Article
Speculative Decoding for 2x Faster Whisper Inference
ā¢
21
Article
Improving Prompt Consistency with Structured Generations
ā¢
61
upvoted
a
paper
11 months ago
upvoted
a
paper
about 1 year ago
upvoted
a
paper
over 1 year ago