Ruslan S.'s picture

3 10 2

Ruslan S.

poedator

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 1 month ago

Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story

commented on their article 10 months ago

4D masks support in Transformers

commented on their article 10 months ago

4D masks support in Transformers

View all activity

Organizations

authored a paper over 1 year ago

SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices

Paper • 2406.02532 • Published Jun 4, 2024 • 13

authored 2 papers almost 2 years ago

SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression

Paper • 2306.03078 • Published Jun 5, 2023 • 3

Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding

Paper • 2402.12374 • Published Feb 19, 2024 • 4