Spaces:

visualisable-ai
/

api

Sleeping

App Files Files Community

api

604 kB

3 contributors

History: 94 commits

gary-boon

Claude Opus 4.5

feat: implement lazy-loading for attention matrices

929ba88 about 1 month ago

.claude
Add Claude Code configuration 3 months ago
.github
fix: Skip heavy ML deps in CI security checks about 2 months ago
backend
feat: implement lazy-loading for attention matrices about 1 month ago
components
Add layer_stride parameter for PromptDiff optimization 5 months ago
docker
Use NGC PyTorch 24.08 for Python 3.10 compatibility about 2 months ago
docs
Add Phase 5: Performance optimizations to phased plan about 2 months ago
runs
Phase 1: DGX Spark infrastructure about 2 months ago
.env.spark.example
772 Bytes

Update .env.spark.example: TORCH_DTYPE now auto-detected about 2 months ago
.gitattributes
1.52 kB

initial commit 6 months ago
.gitignore
499 Bytes

Phase 1: DGX Spark infrastructure about 2 months ago
Dockerfile
1.14 kB

Fix Dockerfile: add build-essential for numcodecs compilation about 2 months ago
FUTURE_CONSIDERATIONS.md
4.11 kB

Add future considerations doc for response size optimization about 2 months ago
README.md
909 Bytes

Update HuggingFace Space description 5 months ago
SECURITY.md
4.45 kB

Add GitHub Actions workflow for security scanning and automated deployment 5 months ago
TESTING.md
4.56 kB

Add Code Llama 7B support with hardware-aware filtering and ICL timeout fixes 3 months ago
TEST_RESULTS.md
6.97 kB

Add Code Llama 7B support with hardware-aware filtering and ICL timeout fixes 3 months ago
app.py
1.69 kB

Fix HuggingFace Spaces cache permission error 6 months ago
explore_vocabulary.py
2.51 kB

Add research attention analysis endpoints with Q/K/V extraction 3 months ago
requirements.txt
605 Bytes

Integrate mistral-common for correct Devstral tokenization about 2 months ago
setup-api-key.md
1.32 kB

Add API key authentication 6 months ago
test_instrumentation.py
8.99 kB

Add research attention analysis endpoints with Q/K/V extraction 3 months ago
test_multi_model.py
8.61 kB

Add Code Llama 7B support with hardware-aware filtering and ICL timeout fixes 3 months ago