COMMITS
September 29, 2024
A
chore: Bump version
Andrei Betlen committed
A
feat: Update llama.cpp
Andrei Betlen committed
September 26, 2024
A
feat: Expose libggml in internal APIs (#1761)
Andrei committed
A
feat: Update llama.cpp
Andrei Betlen committed
A
fix: Additional fixes for speculative decoding
Andrei Betlen committed
X
misc: Rename all_text to remaining_text (#1658)
Xu Song committed
A
fix: Fix speculative decoding
Andrei Betlen committed
September 25, 2024
A
fix: install build dependency
Andrei Betlen committed
A
fix: install build dependency
Andrei Betlen committed
A
chore: Bump version
Andrei Betlen committed
A
feat: Update llama.cpp
Andrei Betlen committed
September 22, 2024
A
feat: Update llama.cpp
Andrei Betlen committed
September 20, 2024
D
chore(deps): bump actions/cache from 3 to 4 (#1751)
dependabot[bot] committed
O
docs: Add cuda 12.5 to README.md (#1750)
Olivier DEBAUCHE committed
A
feat: Add option to configure n_ubatch
Andrei Betlen committed
A
feat: Update llama.cpp
Andrei Betlen committed
September 19, 2024
J
A
X
fix: Fix memory allocation of ndarray (#1704)
Xu Song committed
A
misc: Format
Andrei Betlen committed
A
feat: Update llama.cpp
Andrei Betlen committed
A
feat: Update sampling API for llama.cpp (#1742)
Andrei committed
September 18, 2024
D
chore(deps): bump pypa/cibuildwheel from 2.20.0 to 2.21.1 (#1743)
dependabot[bot] committed
O
feat(ci): Speed up CI workflows using `uv`, add support for CUDA 12.5 wheels
Olivier DEBAUCHE committed
September 6, 2024
A
feat: Update llama.cpp
Andrei Betlen committed
September 5, 2024
A
feat: Update llama.cpp
Andrei Betlen committed
September 2, 2024
A
feat: Update llama.cpp
Andrei Betlen committed
August 31, 2024
A
feat: Update llama.cpp
Andrei Betlen committed
August 30, 2024
A
feat: Update llama.cpp
Andrei Betlen committed
A
fix: Use system message in og qwen format. Closes #1697
Andrei Betlen committed