Ashwin Bharambe 70a7e4d51e fix: unhide python_start, python_end		2025-04-11 20:30:44 -07:00
..
llama3	fix: llama3 bf16 model load	2025-04-09 01:10:49 -07:00
llama3_1	feat: introduce llama4 support (#1877)	2025-04-05 11:53:35 -07:00
llama3_2	refactor: move all llama code to models/llama out of meta reference (#1887)	2025-04-07 15:03:58 -07:00
llama3_3	chore: remove dependency on llama_models completely (#1344)	2025-03-01 12:48:08 -08:00
llama4	fix: unhide python_start, python_end	2025-04-11 20:30:44 -07:00
resources	feat: introduce llama4 support (#1877)	2025-04-05 11:53:35 -07:00
__init__.py	feat: introduce llama4 support (#1877)	2025-04-05 11:53:35 -07:00
checkpoint.py	refactor: move all llama code to models/llama out of meta reference (#1887)	2025-04-07 15:03:58 -07:00
datatypes.py	refactor: move all llama code to models/llama out of meta reference (#1887)	2025-04-07 15:03:58 -07:00
hadamard_utils.py	refactor: move all llama code to models/llama out of meta reference (#1887)	2025-04-07 15:03:58 -07:00
prompt_format.py	refactor: move all llama code to models/llama out of meta reference (#1887)	2025-04-07 15:03:58 -07:00
quantize_impls.py	fix: on-the-fly int4 quantize parameter (#1920)	2025-04-09 15:00:12 -07:00
sku_list.py	refactor: move all llama code to models/llama out of meta reference (#1887)	2025-04-07 15:03:58 -07:00
sku_types.py	refactor: move all llama code to models/llama out of meta reference (#1887)	2025-04-07 15:03:58 -07:00