COMMITS
/ examples/models/llava/model.py May 12, 2025
M
[llava] Remove torch.jit.save in llava example
Mengwei Liu committed
May 6, 2025
P
Refactor attention v2 (#10707)
pytorchbot committed
April 10, 2025
P
[Executorch][llama] Renamed quantized_kv_cache to custom_kv_cache (#10061)
pytorchbot committed
March 26, 2025
February 7, 2025
M
Add BUCK files for llava python and C++ libs
Mengwei Liu 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 23, 2025
K
[ExecuTorch][BE] Split kv cache and SDPA for better code sharing
Kimish Patel committed
October 16, 2024
M
Codemod examples/models/llama2 to examples/models/llama (#6302)
Mergen Nachin committed
August 29, 2024
M
[llava] Quantize embedding
Mengwei Liu committed
August 27, 2024
M
[llava] Expose max_seq_len as a parameter to export_llava
Mengwei Liu committed
August 26, 2024
M
[llava] Enable dynamic shape for image preprocessor
Mengwei Liu committed
August 23, 2024
M
Reduce the memory usage of logits from O(context_length) to O(1)
Mengtao Yuan committed
August 14, 2024
M
[llava] Use huggingface LLaVA instead of depending on third-party/LLaVa
Mengwei Liu committed
August 9, 2024
M
Fix llava model definition for export
Mengwei Liu committed
July 30, 2024
M
Add an option to turn on/off sdpa_with_kv_cache (#4444)
Mengwei Liu committed
July 23, 2024
M
Disable sdpa_with_kv_cache for now (#4319)
Mengwei Liu committed
July 18, 2024
M
Add Llava model definition (#4259)
Mengwei Liu committed
July 16, 2024
M
Rename llava_encoder to llava (#4242)
Mengwei Liu committed