Billy Cao
|
c471871d0b
|
make n_gpu_layers=-1 offload all layers
|
2023-08-13 11:21:28 +08:00 |
|
Billy Cao
|
d018c7b01d
|
Add doc string for n_gpu_layers argument
|
2023-08-12 18:41:47 +08:00 |
|
Andrei Betlen
|
66fb0345e8
|
Move grammar to function call argument
|
2023-08-08 15:08:54 -04:00 |
|
Andrei Betlen
|
1e844d3238
|
fix
|
2023-08-08 15:07:28 -04:00 |
|
Andrei Betlen
|
843b7ccd90
|
Merge branch 'main' into c0sogi/main
|
2023-08-08 14:43:02 -04:00 |
|
Andrei Betlen
|
d015bdb4f8
|
Add mul_mat_q option
|
2023-08-08 14:35:06 -04:00 |
|
Andrei Betlen
|
f6a7850e1a
|
Update llama.cpp
|
2023-08-08 14:30:58 -04:00 |
|
c0sogi
|
0d7d2031a9
|
prevent memory access error by llama_grammar_free
|
2023-08-07 17:02:33 +09:00 |
|
c0sogi
|
b07713cb9f
|
reset grammar for every generation
|
2023-08-07 15:16:25 +09:00 |
|
c0sogi
|
418aa83b01
|
Added grammar based sampling
|
2023-08-07 02:21:37 +09:00 |
|
c0sogi
|
ac188a21f3
|
Added low level grammar API
|
2023-08-05 14:43:35 +09:00 |
|
Andrei Betlen
|
ce57920e60
|
Suppress llama.cpp output when loading model.
|
2023-07-28 14:45:18 -04:00 |
|
Andrei Betlen
|
a9b9f0397c
|
Format
|
2023-07-28 01:53:08 -04:00 |
|
Andrei Betlen
|
abc538fcd5
|
fix: annoying bug where attribute exceptions were droining out file not found exceptions
|
2023-07-28 01:43:00 -04:00 |
|
Shouyi Wang
|
426dbfe3f4
|
Change tensor_split from array to pointer
|
2023-07-25 18:29:59 +10:00 |
|
Andrei Betlen
|
11dd2bf382
|
Add temporary rms_norm_eps parameter
|
2023-07-24 14:09:24 -04:00 |
|
Andrei Betlen
|
8cd64d4ac3
|
Add rms_eps_norm
|
2023-07-24 13:52:12 -04:00 |
|
bretello
|
0f09f10e8c
|
add support for llama2 70b
|
2023-07-24 19:38:24 +02:00 |
|
Andrei Betlen
|
401309d11c
|
Revert "Merge pull request #521 from bretello/main"
This reverts commit 07f0f3a386, reversing
changes made to d8a3ddbb1c.
|
2023-07-24 13:11:10 -04:00 |
|
Andrei
|
07f0f3a386
|
Merge pull request #521 from bretello/main
raise exception when `llama_load_model_from_file` fails
|
2023-07-24 13:09:28 -04:00 |
|
Andrei Betlen
|
d8a3ddbb1c
|
Update llama.cpp
|
2023-07-24 13:08:06 -04:00 |
|
Andrei Betlen
|
985d559971
|
Update llama.cpp
|
2023-07-24 13:04:34 -04:00 |
|
bretello
|
8be7d67f7e
|
raise exception when llama_load_model_from_file fails
|
2023-07-24 14:42:37 +02:00 |
|
Andrei Betlen
|
b83728ad1e
|
Update llama.cpp
|
2023-07-21 12:33:27 -04:00 |
|
Andrei Betlen
|
01435da740
|
Update llama.cpp
|
2023-07-20 18:54:25 -04:00 |
|
Andrei Betlen
|
28a111704b
|
Fix compatibility with older python versions
|
2023-07-20 18:52:10 -04:00 |
|
Andrei Betlen
|
d10ce62714
|
Revert ctypes argtype change
|
2023-07-20 18:51:53 -04:00 |
|
Andrei
|
365d9a4367
|
Merge pull request #481 from c0sogi/main
Added `RouteErrorHandler` for server
|
2023-07-20 17:41:42 -04:00 |
|
Vinicius
|
a8551477f5
|
Update llama_cpp.py - Fix c_char_p to Array[c_char_p] and c_float to Array[c_float]
|
2023-07-20 17:29:11 -03:00 |
|
Carlos Tejada
|
0756a2d3fb
|
Now the last token sent when stream=True
|
2023-07-19 22:47:14 -04:00 |
|
shutup
|
5ed8bf132f
|
expose RoPE param to server start
|
2023-07-18 16:34:36 +08:00 |
|
c0sogi
|
1551ba10bd
|
Added RouteErrorHandler for server
|
2023-07-16 14:57:39 +09:00 |
|
Andrei Betlen
|
8ab098e49d
|
Re-order Llama class params
|
2023-07-15 15:35:08 -04:00 |
|
Andrei Betlen
|
e4f9db37db
|
Fix context_params struct layout
|
2023-07-15 15:34:55 -04:00 |
|
Andrei Betlen
|
f0797a6054
|
Merge branch main into custom_rope
|
2023-07-15 15:11:01 -04:00 |
|
randoentity
|
3f8f276f9f
|
Add bindings for custom_rope
|
2023-07-10 17:37:46 +02:00 |
|
Andrei Betlen
|
a86bfdf0a5
|
bugfix: truncate completion max_tokens to fit context length by default
|
2023-07-09 18:13:29 -04:00 |
|
Andrei Betlen
|
6f70cc4b7d
|
bugfix: pydantic settings missing / changed fields
|
2023-07-09 18:03:31 -04:00 |
|
Andrei
|
5d756de314
|
Merge branch 'main' into add_unlimited_max_tokens
|
2023-07-08 02:37:38 -04:00 |
|
Andrei
|
b8e0bed295
|
Merge pull request #453 from wu-qing-157/main
Fix incorrect token_logprobs (due to indexing after sorting)
|
2023-07-08 02:31:52 -04:00 |
|
Andrei Betlen
|
d6e6aad927
|
bugfix: fix compatibility bug with openai api on last token
|
2023-07-08 00:06:11 -04:00 |
|
Andrei Betlen
|
4f2b5d0b53
|
Format
|
2023-07-08 00:05:10 -04:00 |
|
Andrei Betlen
|
34c505edf2
|
perf: convert pointer to byref
|
2023-07-07 22:54:07 -04:00 |
|
Andrei Betlen
|
52753b77f5
|
Upgrade fastapi to 0.100.0 and pydantic v2
|
2023-07-07 21:38:46 -04:00 |
|
Andrei Betlen
|
11eae75211
|
perf: avoid allocating new buffers during sampling
|
2023-07-07 19:28:53 -04:00 |
|
Andrei Betlen
|
a14d8a9b3f
|
perf: assign to candidates data structure instead
|
2023-07-07 18:58:43 -04:00 |
|
wu-qing-157
|
9e61661518
|
fix indexing token_logprobs after sorting
|
2023-07-07 10:18:49 +00:00 |
|
Andrei Betlen
|
57d8ec3899
|
Add setting to control request interruption
|
2023-07-07 03:37:23 -04:00 |
|
Andrei Betlen
|
4c7cdcca00
|
Add interruptible streaming requests for llama-cpp-python server. Closes #183
|
2023-07-07 03:04:17 -04:00 |
|
Andrei Betlen
|
98ae4e58a3
|
Update llama.cpp
|
2023-07-06 17:57:56 -04:00 |
|