8000 Update CHANGELOG · zhutony/llama-cpp-python@60119db · GitHub
[go: up one dir, main page]
Skip to content

Commit 60119db

Browse files
abetlenabetlen
committed
Update CHANGELOG
1 parent 0449d29 commit 60119db

File tree

1 file changed

+2
-0
lines changed

1 file changed

+2
-0
lines changed

‎CHANGELOG.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -7,10 +7,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
77

88
## [Unreleased]
99

10+
- Add NUMA support. **NOTE** low level api users must call llama_backend_init at the start of their programs by abetlen in f4090a0bb2a2a25acfe28d31c82cc1aa273bedee
1011
- Fix tensor_split server cli argument by @abetlen in c4c440ba2dc86d9de728a751311fdd1c8e3756fa
1112
- Made all `Llama` init parameters into keyword-only parameters by @abetlen in c8f9b8a734b5b040379bbd93995ba177affab1fe
1213
- Added server params f 55D2 or `low_vram`, `main_gpu`, `lora_base`, and `lora_path` by @abetlen in 2920c4bf7ee1412d6bba7846e0e1b7ef6d34043b
1314
- Removed server params for `rms_norm_eps` and `n_gqa` by @abetlen in 2920c4bf7ee1412d6bba7846e0e1b7ef6d34043b
15+
- Fix boolean cli options by @abetlen in c999325e8e4507f6c6249dd2fb8de7f8bf57f71e and 0449d29b9f940e437231a07b9d56550226558bac
1416

1517
## [0.2.3]
1618

0 commit comments

Comments
 (0)
0