COMMITS
/ examples/models/llama/llama_transformer.py May 6, 2025
P
Refactor attention v2 (#10707)
pytorchbot committed
March 6, 2025
M
Add qk norm optionally before attention calculation
madhu-fb committed
February 25, 2025
M
Fix pyre error for logits
Mengtao Yuan committed
M
etLLM: add options to apply embedding or output. (#8653)
Mengtao Yuan committed
February 7, 2025
S
Static attention implementation
Shen Chen Xu committed
February 6, 2025
S
Pass ForwardOptions from top level module and also return any relevant state as output
Shen Chen Xu committed
February 1, 2025
M
Add abstract base class for attention mechanisms with unified interface
Mengtao Yuan committed
January 30, 2025
P
January 23, 2025
K
[ExecuTorch][BE] Split kv cache and SDPA for better code sharing
Kimish Patel committed
December 11, 2024
M
Fix hardcoded rope_scale factor to 32 for Llama 3.2
Mergen Nachin committed
November 27, 2024
P
move rope related logic together (#7113)
pytorchbot committed
November 25, 2024
P
allow customized head_dim (#7065)
pytorchbot committed
November 11, 2024
C
Qualcomm AI Engine Direct - Add llama sha transforming pass
Chun-I Tsai committed
October 25, 2024
C
Set member variable to Attention module (#6376)
Chun-I Tsai committed
October 22, 2024
N
llama export with input vocab pruning
Naveen Suda committed
October 21, 2024
H
[ET-VK][ez] Apply rotary embedding as Module (#6422)
Hansong committed
October 20, 2024
M
Fix params.json for llama models
Mergen Nachin committed
October 16, 2024
M
Codemod examples/models/llama2 to examples/models/llama (#6302)
Mergen Nachin committed