Hugging Face's logo

Spaces:
TiGa-RCE
/
embedding-quantization-cuda-control
Running on Zero

App Files Community
embedding-quantization-cuda-control

Commit History

Finalize public CUDA control documentation
ed72f18
Running
verified

TiGa-RCE commited on

Add direct-load BF16 repeat comparison
647387b
verified

TiGa-RCE commited on

Add bounded larger-family CUDA quantizer controls
bcba9be
verified

TiGa-RCE commited on

Deduplicate existing Accelerate requirement
4d45df1
verified

TiGa-RCE commited on

Load 8B directly inside allocated ZeroGPU call
7740aa9
verified

TiGa-RCE commited on

Switch larger-family control to root-loaded Qwen3 8B
bd2dad5
verified

TiGa-RCE commited on

Disable unused KV cache for embedding controls
97e5e64
verified

TiGa-RCE commited on

Expose larger-family benchmark traceback
2fad4af
verified

TiGa-RCE commited on

Isolate GTE startup packing from completed 0.6B model
234931c
verified

TiGa-RCE commited on

Move GTE 1.5B CUDA placement to ZeroGPU startup
88534d9
verified

TiGa-RCE commited on

Add mounted 1.5B and 8B BF16 cross-runtime controls
7973967
verified

TiGa-RCE commited on

Lazy-load CUDA quantizer configuration inside GPU call
22338c1
verified

TiGa-RCE commited on

Add bounded bitsandbytes INT8 and NF4 controls
1a6347c
verified

TiGa-RCE commited on

Add bounded ZeroGPU BF16 CUDA control
bc3f111
verified

TiGa-RCE commited on

initial commit
695f3b6
verified

TiGa-RCE commited on