File tree Expand file tree Collapse file tree 2 files changed +18
-1
lines changed
Filter options
Expand file tree Collapse file tree 2 files changed +18
-1
lines changed
Original file line number Diff line number Diff line change @@ -7,6 +7,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
77
88## [ Unreleased]
99
10+ ## [ 0.2.12]
11+
12+ - Update llama.cpp to ggerganov/llama.cpp@50337961a678fce4081554b24e56e86b67660163
13+ - Fix missing ` n_seq_id ` in ` llama_batch ` by @NickAlgra in #842
14+ - Fix exception raised in ` __del__ ` when freeing models by @cebtenzzre in #848
15+ - Performance improvement for logit bias by @zolastro in #851
16+ - Fix suffix check arbitrary code execution bug by @mtasic85 in #854
17+ - Fix typo in ` function_call ` parameter in ` llama_types.py ` by @akatora28 in #849
18+ - Fix streaming not returning ` finish_reason ` by @gmcgoldr in #798
19+ - Fix ` n_gpu_layers ` check to allow values less than 1 for server by @hxy9243 in #826
20+ - Supppress stdout and stderr when freeing model by @paschembri in #803
21+ - Fix ` llama2 ` chat format by @delock in #808
22+ - Add validation for tensor_split size by @eric1932 #820
23+ - Print stack trace on server error by @abetlen in d6a130a052db3a50975a719088a9226abfebb266
24+ - Update docs for gguf by @johnccshen in #783
25+ - Add ` chatml ` chat format by @abetlen in 305482bd4156c70802fc054044119054806f4126
26+
1027## [ 0.2.11]
1128
1229- Fix bug in ` llama_model_params ` object has no attribute ` logits_all ` by @abetlen in d696251fbe40015e8616ea7a7d7ad5257fd1b896
Original file line number Diff line number Diff line change 11from .llama_cpp import *
22from .llama import *
33
4- __version__ = "0.2.11 "
4+ __version__ = "0.2.12 "
You can’t perform that action at this time.
0 commit comments