llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00

Files

Aleksei Nikiforov 7adc79c032 gguf-py : add support for endian conversion of BF16 data (#16594 )

BF16 requires special handling in this script
while it's a 2-bytes data, but view is 1-byte by default.
Switch to correct view before attempting byteswapping.

With this change correctly byteswapping models like
Meta-Llama-3-8B-Instruct-bf16-GGUF
should be possible.

2025-10-15 22:43:08 +02:00

scripts

gguf-py : add support for endian conversion of BF16 data (#16594 )

2025-10-15 22:43:08 +02:00

__init__.py

convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499 )

2024-07-18 20:40:15 +10:00

constants.py

model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367 )

2025-10-09 09:39:18 +03:00

gguf_reader.py

gguf-py : display the invalid gguf type (#13687 )