Article
From DeepSpeed to FSDP and Back Again with Hugging Face Accelerate
By
and 3 others
•
•
55Tran Quoc Vinh
vinhtran2611
AI & ML interests
None yet
Recent Activity
liked
a dataset
about 1 month ago
5CD-AI/Viet-Geometry-VQA
liked
a dataset
about 1 month ago
theblackcat102/IMO-geometry
new activity
3 months ago
huggingface/InferenceSupport:Qwen/Qwen2.5-Coder-0.5B-Instruct
Organizations
upvoted
an
article
about 1 year ago
upvoted
11
papers
over 1 year ago
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Paper
•
2401.10774
•
Published
•
59
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Paper
•
2401.06066
•
Published
•
55
Improving Text Embeddings with Large Language Models
Paper
•
2401.00368
•
Published
•
81
Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws
Paper
•
2401.00448
•
Published
•
31
LLaMA Pro: Progressive LLaMA with Block Expansion
Paper
•
2401.02415
•
Published
•
54
TinyLlama: An Open-Source Small Language Model
Paper
•
2401.02385
•
Published
•
95
Understanding LLMs: A Comprehensive Overview from Training to Inference
Paper
•
2401.02038
•
Published
•
66
Mixtral of Experts
Paper
•
2401.04088
•
Published
•
160
PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU
Paper
•
2312.12456
•
Published
•
44
Gemini: A Family of Highly Capable Multimodal Models
Paper
•
2312.11805
•
Published
•
46
LLM in a flash: Efficient Large Language Model Inference with Limited Memory
Paper
•
2312.11514
•
Published
•
257