You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: CHANGELOG.md
+2Lines changed: 2 additions & 0 deletions
Original file line number
Diff line number
Diff line change
@@ -7,10 +7,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
7
7
8
8
## [Unreleased]
9
9
10
+
- Add NUMA support. **NOTE** low level api users must call llama_backend_init at the start of their programs by abetlen in f4090a0bb2a2a25acfe28d31c82cc1aa273bedee
10
11
- Fix tensor_split server cli argument by @abetlen in c4c440ba2dc86d9de728a751311fdd1c8e3756fa
11
12
- Made all `Llama` init parameters into keyword-only parameters by @abetlen in c8f9b8a734b5b040379bbd93995ba177affab1fe
12
13
- Added server params for `low_vram`, `main_gpu`, `lora_base`, and `lora_path` by @abetlen in 2920c4bf7ee1412d6bba7846e0e1b7ef6d34043b
13
14
- 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
0 commit comments