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

COMMITS

/ examples/models/llama/model.py
test
May 6, 2025
P
Refactor attention v2 (#10707)
pytorchbot committed
e196b50
April 18, 2025
S
Support pre-quantization via torchao quantize_ (#10293)
Scott Roy committed
15888ca
March 27, 2025
J
Remove exception fall back on checkpoint loading (#9660)
Jack committed
5098808
March 26, 2025
M
Default Uninitialized Llama2 Weights to Zeros, and Provide Better Quantization for Example Models (#9634)
Max Ren committed
91be93c
J
Add export_llama performance regression test using expected ops (#9158)
Jack committed
2f65c3a
March 22, 2025
J
Make export llama checkpoint and param optional
Jack committed
de0f6f1
March 21, 2025
J
Refactor dtype handling in export_llama
Jack committed
0c1c362
February 25, 2025
J
Add tests for qwen + allow uninitialized weights in Llama model (#8552)
Jack committed
0add080
February 14, 2025
J
Eliminate confusion about meta weights during quantization (#8487)
Jack committed
08eb5be
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
Add abstract base class for attention mechanisms with unified interface
Mengtao Yuan committed
a972e73
January 30, 2025
P
[Excutorch][Llama] Decouple input sequence length from kv cache context length (#8047)
pytorchbot committed
afc5a50
December 11, 2024
M
Fix hardcoded rope_scale factor to 32 for Llama 3.2
Mergen Nachin committed
957259e
December 2, 2024
P
Transform model to be able to use Attention Sink
pytorchbot committed
aa67cd9
October 22, 2024
N
llama export with input vocab pruning
Naveen Suda committed
89ba47a
October 20, 2024
M
Fix params.json for llama models
Mergen Nachin committed
46ea1a4
October 16, 2024
M
Codemod examples/models/llama2 to examples/models/llama (#6302)
Mergen Nachin committed
63f0718