Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
261712.8
TFLOPS
3
3
50
Wei Wu
Wei-Wu
Follow
droussis's profile picture
1 follower
·
10 following
AI & ML interests
None yet
Recent Activity
liked
a model
3 days ago
jiulaikankan/Qwen2.5-14B-ReasonGenRM
commented
on
a paper
about 1 month ago
Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy
reacted
to
codelion
's
post
with 🔥
about 1 month ago
🚀 Just published: "OpenEvolve: Open-Source Evolutionary Code Optimization with Real-World GPU Kernel Discovery" We built the first open-source implementation of Google's AlphaEvolve system and used it to automatically discover GPU kernel optimizations that outperform human engineers! Key results: - 21.8% average decode speed improvement on Apple Silicon - 36.7% improvement on long-context transformer attention - Discovered novel vectorization patterns and 2-pass softmax algorithm The system evolved a Metal kernel for Qwen3's Grouped Query Attention from a basic 3-pass implementation into something with sophisticated Apple Silicon optimizations that would take experts months to discover manually. The evolved kernel automatically found the optimal vec<T,8> operations for 128-dim attention heads and fused softmax computation with value accumulation. Really excited about the potential here - imagine evolutionary algorithms automatically discovering optimizations across all our AI infrastructure. What would you want to optimize with this approach? Full write-up: https://huggingface.co/blog/codelion/openevolve-gpu-kernel-discovery GitHub: https://github.com/codelion/openevolve #AI #MachineLearning #GPU #OpenSource #Evolution #CodeOptimization #TransformerOptimization
View all activity
Organizations
Wei-Wu
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a model
3 days ago
jiulaikankan/Qwen2.5-14B-ReasonGenRM
Text Generation
•
15B
•
Updated
Dec 27, 2024
•
2
•
1
liked
a model
about 1 month ago
tencent/Hunyuan-A13B-Instruct
Text Generation
•
80B
•
Updated
14 days ago
•
13.1k
•
777
liked
3 models
5 months ago
RekaAI/reka-flash-3
21B
•
Updated
Mar 13
•
1.26k
•
380
google/gemma-3-27b-it
Image-Text-to-Text
•
27B
•
Updated
Mar 21
•
362k
•
•
1.54k
moonshotai/Moonlight-16B-A3B-Instruct
Text Generation
•
16B
•
Updated
Mar 3
•
16k
•
177
liked
3 models
6 months ago
QuixiAI/DeepSeek-V3-AWQ
Text Generation
•
Updated
Mar 29
•
1.29k
•
35
xwen-team/Xwen-7B-Chat
Text Generation
•
8B
•
Updated
Feb 4
•
24
•
32
mistralai/Mistral-Small-24B-Instruct-2501
24B
•
Updated
8 days ago
•
70.2k
•
934
liked
a dataset
7 months ago
HumanLLMs/Human-Like-DPO-Dataset
Viewer
•
Updated
Jan 12
•
10.9k
•
1.16k
•
231
liked
a model
7 months ago
hexgrad/Kokoro-82M
Text-to-Speech
•
Updated
Apr 10
•
1.92M
•
•
4.78k
liked
a model
8 months ago
Efficient-Large-Model/Sana_1600M_1024px
Text-to-Image
•
Updated
Jan 10
•
544
•
•
212
liked
a Space
9 months ago
Running
2.48k
2.48k
Anycoder
🏢
Generate HTML/CSS/JS code for web projects
liked
2 datasets
11 months ago
G-reen/Duet-v0.5
Viewer
•
Updated
Aug 27, 2024
•
5k
•
18
•
20
NousResearch/hermes-function-calling-v1
Viewer
•
Updated
Aug 30, 2024
•
11.6k
•
1.85k
•
325
liked
2 models
12 months ago
black-forest-labs/FLUX.1-dev
Text-to-Image
•
Updated
Jun 27
•
1.53M
•
•
11.1k
NCSOFT/Llama-3-OffsetBias-RM-8B
Text Classification
•
8B
•
Updated
Sep 6, 2024
•
93
•
23
liked
a model
about 1 year ago
Nexusflow/Athene-70B
Text Generation
•
71B
•
Updated
Nov 15, 2024
•
2.05k
•
•
199
liked
3 datasets
about 1 year ago
instruction-pretrain/ft-instruction-synthesizer-collection
Viewer
•
Updated
Mar 1
•
249k
•
155
•
62
BAAI/Infinity-Instruct
Viewer
•
Updated
Jun 17
•
21.9M
•
3.24k
•
653
dell-research-harvard/AmericanStories
Updated
Mar 26
•
5.04k
•
149
Load more