Mostafa Elhoushi's picture

33 4

Mostafa Elhoushi

melhoushi

·

AI & ML interests

Make ML faster, smaller, smarter.

Recent Activity

authored a paper about 22 hours ago

CHAI: Clustered Head Attention for Efficient LLM Inference

authored a paper about 22 hours ago

Characterizing and Efficiently Accelerating Multimodal Generation Model Inference

authored a paper about 22 hours ago

Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs

View all activity

Organizations

commented a paper 1 day ago

any4: Learned 4-bit Numeric Representation for LLMs

Paper • 2507.04610 • Published 3 days ago • 4 •

commented a paper 7 months ago

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Paper • 2404.16710 • Published Apr 25, 2024 • 80 •

New activity in facebook/layerskip-llama2-13B 9 months ago

Adding `safetensors` variant of this model

#1 opened 9 months ago by

New activity in facebook/layerskip-llama2-7B 9 months ago

Adding `safetensors` variant of this model

#1 opened 9 months ago by

New activity in apple/OpenELM-3B-Instruct 11 months ago

Tokenizer related issues / errors

#4 opened about 1 year ago by

New activity in facebook/superblock-vit-b-16 about 1 year ago

rename sp0.90-ts64

#25 opened about 1 year ago by

rename sp0.90-ts32

#24 opened about 1 year ago by

rename sp0.90-ts32

#23 opened about 1 year ago by

rename sp0.90-ts16

#22 opened about 1 year ago by

rename sp0.88-ts64

#21 opened about 1 year ago by

rename sp0.88-ts32

#20 opened about 1 year ago by

rename sp0.88-ts16

#19 opened about 1 year ago by

rename sp0.86-ts64

#18 opened about 1 year ago by

rename sp0.86-ts32

#17 opened about 1 year ago by

rename sp0.86-ts16

#16 opened about 1 year ago by

rename sp0.84-ts64

#15 opened about 1 year ago by

rename sp0.84-ts32

#14 opened about 1 year ago by

rename sp0.84-ts16

#13 opened about 1 year ago by

rename sp0.82-ts64

#12 opened about 1 year ago by

rename sp0.82-ts32

#11 opened about 1 year ago by