Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Spaces:
atharv6f
/
flash-attention-explorer
like
0
Sleeping
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
flash-attention-explorer
/
src
153 kB
Ctrl+K
Ctrl+K
1 contributor
History:
28 commits
a0y0346
Fix Online Softmax: move subplot titles inside chart area (y=0.95)
7720e5f
3 months ago
__init__.py
Safe
43 Bytes
Phase 1: Core structure with model configs and placeholder tabs
3 months ago
attention_utils.py
Safe
13.6 kB
fix: Add fallback SDPA benchmark when attention layer fails
3 months ago
benchmark.py
Safe
37.3 kB
fix: Add fallback SDPA benchmark when attention layer fails
3 months ago
constants.py
Safe
2.85 kB
Add H200 GPU support and improve roofline chart visibility
3 months ago
gqa.py
Safe
21.9 kB
Fix GQA scaling chart x-axis: use log scale to space tick labels properly
3 months ago
memory_budget.py
Safe
19.7 kB
Add separate KV Cache dtype selector (FP16/BF16/FP8/INT8)
3 months ago
models.py
Safe
6.05 kB
Phase 1: Core structure with model configs and placeholder tabs
3 months ago
prefill_decode.py
Safe
35.6 kB
Refactor benchmarks to use real model.config values
3 months ago
visualizer.py
Safe
15.7 kB
Fix Online Softmax: move subplot titles inside chart area (y=0.95)
3 months ago