Skip to content

Commit a9fe0f8

Browse files
committedDec 9, 2024
chore: Bump version
1 parent 61508c2 commit a9fe0f8

File tree

2 files changed

+15
-1
lines changed

2 files changed

+15
-1
lines changed
 

Diff for: ‎CHANGELOG.md

+14
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
77

88
## [Unreleased]
99

10+
## [0.3.3]
11+
12+
- feat: Update llama.cpp to ggerganov/llama.cpp@ce8784bdb153ff7794dde5a50b0ebfa51baa6171
13+
- fix: chat API logprobs format by @domdomegg in #1788
14+
- feat: Add support for CUDA 12.6, fix CUDA 12.5 by @Smartappli in #1775
15+
- fix: Make content not required in ChatCompletionRequestAssistantMessage by @feloy in #1807
16+
- fix: Fix pickling of Llama class by setting seed from _seed member by @abetlen in 2523472c3eccb9ab9277117cc4ff705212b6888a
17+
- fix: Fix logit-bias type hint by @ddh0 in #1802
18+
- fix(server): Avoid thread starvation on many concurrent requests by making use of asyncio to lock llama_proxy context by @gjpower in #1798
19+
- fix(server): Added missing exit_stack.close() to /v1/chat/completions by @Ian321 in #1796
20+
- fix(examples): Refactor Batching notebook to use new sampler chain API by @lukestanley in #1793
21+
- fix(docs): Update development instructions by @Florents-Tselai in #1833
22+
- fix(docs): Remove ref to llama_eval in llama_cpp.py docs by @richdougherty in #1819
23+
1024
## [0.3.2]
1125

1226
- feat: Update llama.cpp to ggerganov/llama.cpp@74d73dc85cc2057446bf63cc37ff649ae7cebd80

Diff for: ‎llama_cpp/__init__.py

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
11
from .llama_cpp import *
22
from .llama import *
33

4-
__version__ = "0.3.2"
4+
__version__ = "0.3.3"

0 commit comments

Comments
 (0)