Morph MORPH
SIGN IN SIGN UP
dhruvhead / executorch UNCLAIMED
0 0 1 Python

COMMITS

/ examples/models/llama/attention.py
test
May 13, 2025
P
[Executorch][llm] Enable leveraging ring kv cache via module swap (#10835)
pytorchbot committed
ef30b25
P
[Executorch][llm] Add ring buffer based kv cache and mask calculation to MHA (#10833)
pytorchbot committed
0bb059f
P
[Executorch][llm] Add support for ring kv cache and ring attention (#10832)
pytorchbot committed
d7201ab
April 29, 2025
J
Add Qwen3 0.6B, 1.7B, and 4B (#10539)
Jack committed
7b86bf1
March 6, 2025
M
Add qk norm optionally before attention calculation
madhu-fb committed
352416e
February 24, 2025
J
Add qwen 2.5 (#8355)
Jack committed
2859e47
February 7, 2025
S
Static attention implementation
Shen Chen Xu committed
513e92d
February 6, 2025
S
Pass ForwardOptions from top level module and also return any relevant state as output
Shen Chen Xu committed
b362ab7
February 1, 2025
M
Single location to update optional args for all attentions
Mengtao Yuan committed
a5c7609
M
Add abstract base class for attention mechanisms with unified interface
Mengtao Yuan committed
a972e73