baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
1359 commits 1 branch 0 tags 2.1 MiB
Commit graph

570 commits

Author SHA1 Message Date
anil
cfb7da98ed
Support Accept text/event-stream in chat and completion endpoints, resolves #1083 (#1088) 
Co-authored-by: Anil Pathak <anil@heyday.com>
Co-authored-by: Andrei Betlen <abetlen@gmail.com>
 2024-01-16 12:52:52 -05:00
Andrei Betlen
4b11fa83c0 Bump version 2024-01-15 12:54:51 -05:00
Andrei Betlen
84615adbc6 Add split_mode option. Closes #1085 2024-01-15 12:49:20 -05:00
Phil H
76aafa6149
Implement GGUF metadata KV overrides (#1011) 
* Implement GGUF metadata overrides

* whitespace fix

* Fix kv overrides.

* Fix pointer and pickle

* Match llama.cpp kv_overrides cli argument

---------

Co-authored-by: Andrei <abetlen@gmail.com>
 2024-01-15 12:29:29 -05:00
yieldthought
7eff42c239
Avoid "LookupError: unknown encoding: ascii" when open() called in a destructor (#1012) 
The existing code often causes "LookupError: unknown encoding: ascii" when open() called in a destructor. Saving open in self.open is not enough to avoid this. Instead, we can avoid reopening /dev/null every time by doing it once when the module is loaded.
 2024-01-15 10:52:10 -05:00
Mark Neumann
c689ccc728
Fix Pydantic model parsing (#1087) 2024-01-15 10:45:57 -05:00
Andrei Betlen
5502ac8876 Update llama.cpp 2024-01-15 10:12:10 -05:00
Andrei Betlen
359ae73643 Update llama.cpp 2024-01-14 08:17:22 -05:00
Andrei Betlen
7c898d5684 Update llama.cpp 2024-01-13 22:37:49 -05:00
Andrei Betlen
bb610b9428 Update llama.cpp 2024-01-11 22:51:12 -05:00
Andrei Betlen
f0159663d9 Bump version 2024-01-10 02:51:17 -05:00
Stephen Hankinson
df3be58d6c
Add ability to pass in penalize_nl param (#1068) 2024-01-10 02:46:27 -05:00
Joseph Turian
2ddce7294e
print_grammar to stderr (#1052) 2024-01-10 02:46:03 -05:00
Andrei Betlen
1ae05c102b Update llama.cpp 2024-01-08 14:51:29 -05:00
Andrei Betlen
75d0527fd7 Bump version 2024-01-04 18:30:12 -05:00
Fedor Moiseev
907b9e9d42
Add Saiga chat format. (#1050) 2024-01-04 18:12:58 -05:00
xaviviro
cf743ec5d3
Added ChatGLM chat format (#1059) 
Co-authored-by: Xavier Vinaixa Rosello <xaviviro@MacBook-Pro-de-Xavier.local>
 2024-01-04 18:12:02 -05:00
Andrei Betlen
eb9c7d4ed8 Update llama.cpp 2024-01-03 22:04:04 -05:00
Andrei Betlen
011c3630f5 Bump version 2023-12-27 17:35:02 -05:00
Andrei Betlen
92284f32cb Add HIP_PATH to dll search directories for windows users. 2023-12-22 15:29:56 -05:00
Andrei Betlen
2b0d3f36fa set llama_max_devices using library function 2023-12-22 15:19:28 -05:00
Andrei Betlen
d9a1d90fd7 Fix typo 2023-12-22 15:12:27 -05:00
Andrei Betlen
37556bf9c4 Bump version 2023-12-22 14:55:58 -05:00
Andrei Betlen
6d8bc090f9 fix: inccorect bindings for kv override. Based on #1011 2023-12-22 14:52:20 -05:00
Andrei Betlen
522aecb868 docs: add server config docs 2023-12-22 14:37:24 -05:00
Andrei Betlen
6473796343 Update llama.cpp 2023-12-22 14:10:34 -05:00
swg
4b01a873ef
server: Support none defaulting to infinity for completions (#111) 
* Support defaulting to infinity or -1 for chat completions

* Check if completion_tokens is none in error handler.

* fix: max_tokens in create completion should match openai spec

* Fix __call__

---------

Co-authored-by: Andrei Betlen <abetlen@gmail.com>
 2023-12-22 14:05:13 -05:00
Dave
12b7f2f4e9
[Feat] Multi model support (#931) 
* Update Llama class to handle chat_format & caching

* Add settings.py

* Add util.py & update __main__.py

* multimodel

* update settings.py

* cleanup

* delete util.py

* Fix /v1/models endpoint

* MultiLlama now iterable, app check-alive on "/"

* instant model init if file is given

* backward compability

* revert model param mandatory

* fix error

* handle individual model config json

* refactor

* revert chathandler/clip_model changes

* handle chat_handler in MulitLlama()

* split settings into server/llama

* reduce global vars

* Update LlamaProxy to handle config files

* Add free method to LlamaProxy

* update arg parsers & install server alias

* refactor cache settings

* change server executable name

* better var name

* whitespace

* Revert "whitespace"

This reverts commit bc5cf51c64a95bfc9926e1bc58166059711a1cd8.

* remove exe_name

* Fix merge bugs

* Fix type annotations

* Fix type annotations

* Fix uvicorn app factory

* Fix settings

* Refactor server

* Remove formatting fix

* Format

* Use default model if not found in model settings

* Fix

* Cleanup

* Fix

* Fix

* Remove unnused CommandLineSettings

* Cleanup

* Support default name for copilot-codex models

---------

Co-authored-by: Andrei Betlen <abetlen@gmail.com>
 2023-12-22 05:51:25 -05:00
Andrei Betlen
4a85442c35 Update llama.cpp 2023-12-22 00:12:37 -05:00
twaka
2f03fb0231
fix text_offset of multi-token characters (#1037) 
* fix text_offsets for bytes tokens

* fix
 2023-12-22 00:03:29 -05:00
docmeth02
33cc623346
Implement openai api compatible authentication (#1010) 2023-12-21 13:44:49 -05:00
Andrei Betlen
a05b4da80a fix: float32 is not JSON serializable when streaming logits. 2023-12-18 18:40:36 -05:00
Andrei Betlen
7df6c32544 Fix type annotations 2023-12-18 18:14:53 -05:00
Andrei Betlen
b703aad79e Fix type annotation 2023-12-18 18:13:37 -05:00
Andrei Betlen
d0aedfcff6 Fix type annotation 2023-12-18 18:12:49 -05:00
Eduard Christian Dumitrescu
2993936b10
Fix ctypes definitions of llama_kv_cache_view_update and llama_kv_cache_view_free. (#1028) 2023-12-18 18:11:26 -05:00
Andrei Betlen
5e863d8a3b Bump version 2023-12-18 16:09:18 -05:00
Andrei Betlen
095c650006 Add offload_kqv option to llama and server 2023-12-18 15:36:09 -05:00
Andrei Betlen
472b344ae3 Remove unnused import 2023-12-18 15:32:40 -05:00
kddubey
6b2e0e05b4
perf: Don't convert logprobs arrays to lists (#1021) 2023-12-18 14:28:12 -05:00
Brandon Roberts
62944df142
Bugfix: Remove f16_kv, add offload_kqv field (#1019) 
F16_KV appears to have been removed here: af99c6fbfc

This addresses two issues:

 - #995 which just requests to add the KV cache offloading param
 - #1006 a NULL ptr exception when using the embeddings (introduced by
   leaving f16_kv in the fields struct)
 2023-12-18 14:27:11 -05:00
Daniele Morotti
f1c631dc53
Bug fixed with n_ctx=0 (#1015) 
If the n_ctx is set to 0 the code should use the maximum context length of the selected model, but it didn't work. There was a problem with the initialization of this parameter and a related problem with 'n_batch'.
 2023-12-16 18:59:50 -05:00
kddubey
5a8944672f
Fix logits_to_logprobs for 2-D and 3-D logits (#1002) 
* Fix logits_to_logprobs for 2-D and 3-D logits

* Set dtype to single

* Test size
 2023-12-16 18:59:26 -05:00
Andrei Betlen
534b1ea9b5 Update llama.cpp 2023-12-16 18:57:43 -05:00
Andrei Betlen
cbce061ffd Bump version 2023-12-13 21:52:29 -05:00
yhfgyyf
8b4db732bd
Add qwen chat format (#1005) 2023-12-13 21:43:43 -05:00
Andrei Betlen
690c563b60 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main 2023-12-13 21:43:19 -05:00
Andrei Betlen
c0fc0a1e82 Update llama.cpp 2023-12-13 21:43:16 -05:00
Radoslav Gerganov
8e44a32075
Add support for running the server with SSL (#994) 2023-12-11 20:47:11 -05:00
Tanner Hobson
ef22e478db
Replace logits_to_logprobs implementation with numpy equivalent to llama.cpp (#991) 
See #990. This change makes the logits_to_logprobs function equivalent to the version in the llama.cpp repository. It uses numpy so it's much faster than the previous version.
 2023-12-11 20:46:27 -05:00