Hongyu Shi

HongyuS

·

HongyuS

AI & ML interests

None yet

Recent Activity

liked a model 5 days ago

deepseek-ai/DeepSeek-V4-Pro-DSpark

liked a model 5 days ago

deepseek-ai/DeepSeek-V4-Flash-DSpark

liked a model 12 days ago

baidu/Unlimited-OCR

View all activity

Organizations

upvoted an article 3 months ago

Article

Continuous batching from first principles

+1

ror, ArthurZ, mcpotato

•

Nov 25, 2025

• 417

upvoted 2 collections 3 months ago

DFlash

Block Diffusion for Flash Speculative Decoding • 23 items • Updated 7 days ago • 142

Qwen-3.5-unsloth-mlx

AWQ-style pre-scaling using Unsloth's imatrix calibration data, then 3-6-bit affine quantization with the Unsloth mixed-precision recipe via MLX • 20 items • Updated Mar 29 • 20

upvoted 4 collections over 1 year ago

DeepSeek-R1-Distill

39 items • Updated Feb 26, 2025 • 25

Qwen2.5-1M

10 items • Updated Jan 26, 2025 • 5

Qwen2.5-VL

22 items • Updated Mar 24, 2025 • 11

Llama 3.3

5 items • Updated Dec 6, 2024 • 7

upvoted an article almost 2 years ago

Article

WWDC 24: Running Mistral 7B with Core ML

+2

pcuenq, FL33TW00D-HF, reach-vb, osanseviero

•

Jul 22, 2024

• 65

upvoted 2 collections over 2 years ago

Qwen1.5

Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. • 7 items • Updated Mar 7, 2024 • 3

Qwen1.5

Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. • 53 items • Updated Mar 2 • 214