FazBrowse GitHub Viewer | Trending | | Home

Tools: [Download Repo ZIP] [Original HTTPS Page]

Commits · uid17/llama-cpp-python · GitHub

Commits

Commits on Sep 26, 2024

feat: Expose libggml in internal APIs (#1761)
abetlen
authored
01c7607
feat: Update llama.cpp
abetlen
committed
dca0c9a
fix: Additional fixes for speculative decoding
abetlen
committed
e975dab
misc: Rename all_text to remaining_text (#1658)

xu-song
and
abetlen
authored
11d9562
fix: Fix speculative decoding
abetlen
committed
9992c50

Commits on Sep 25, 2024

fix: install build dependency
abetlen
committed
65222bc
fix: install build dependency
abetlen
committed
8e07db0
chore: Bump version
abetlen
committed
b3dfb42
feat: Update llama.cpp
abetlen
committed
926b414

Commits on Sep 22, 2024

feat: Update llama.cpp
abetlen
committed
4744551

Commits on Sep 20, 2024

chore(deps): bump actions/cache from 3 to 4 (#1751)

dependabot[bot]
and
abetlen
authored
1324c0c
docs: Add cuda 12.5 to README.md (#1750)

Smartappli
and
abetlen
authored
49b1e73
feat: Add option to configure n_ubatch
abetlen
committed
6c44a3f
feat: Update llama.cpp
abetlen
committed
47d7a62

Commits on Sep 19, 2024

feat: Add loading sharded GGUF files from HuggingFace with Llama.from_pretrained(additional_files=[...]) . Closes #1341

Gnurro
and
abetlen
authored
84c0920
fix: Don't store scores internally unless logits_all=True. Reduces memory requirements for large context. Closes #1542
abetlen
committed
29afcfd
fix: Fix memory allocation of ndarray (#1704)

xu-song
and
abetlen
authored
22cedad
misc: Format
abetlen
committed
9b64bb5
feat: Update llama.cpp
abetlen
committed
1e64664
feat: Update sampling API for llama.cpp (#1742)
abetlen
authored
f8fcb3e

Commits on Sep 18, 2024

chore(deps): bump pypa/cibuildwheel from 2.20.0 to 2.21.1 (#1743)

dependabot[bot]
and
abetlen
authored
a4e1451
feat(ci): Speed up CI workflows using `uv`, add support for CUDA 12.5 wheels

Smartappli
and
abetlen
authored
e529940

Commits on Sep 6, 2024

feat: Update llama.cpp
abetlen
committed
c032fc6

Commits on Sep 5, 2024

feat: Update llama.cpp
abetlen
committed
9497bcd

Commits on Sep 2, 2024

feat: Update llama.cpp
abetlen
committed
c3fc80a

Commits on Aug 31, 2024

feat: Update llama.cpp
abetlen
committed
9769e57

Commits on Aug 30, 2024

feat: Update llama.cpp
abetlen
committed
dcb0d0c
fix: Use system message in og qwen format. Closes #1697
abetlen
committed
98eb092

Commits on Aug 29, 2024

feat: Enable detokenizing special tokens with `special=True` (#1596)

benniekiss
and
abetlen
authored
d981d32
docs: Update README
abetlen
committed
9cba3b8
docs: Update README
abetlen
committed
8b853c0
docs: Update README
abetlen
committed
4b1e364
misc(fix): Update CHANGELOG
abetlen
committed
45001ac
chore: Bump version
abetlen
committed
077ecb6
feat: Update llama.cpp
abetlen
committed
332720d

Back | FazBrowse Home | New Git URL