Andrei Betlen
|
f0797a6054
|
Merge branch main into custom_rope
|
2023-07-15 15:11:01 -04:00 |
|
Andrei Betlen
|
f72b6e9b73
|
Update llama.cpp
|
2023-07-15 15:01:08 -04:00 |
|
Andrei
|
15e0e0a937
|
Merge pull request #390 from SubhranshuSharma/main
added termux with root instructions
|
2023-07-14 16:53:23 -04:00 |
|
Andrei Betlen
|
118b7f6d5c
|
fix: tensor_split should be optional list
|
2023-07-14 16:52:48 -04:00 |
|
Andrei Betlen
|
25b3494e11
|
Minor fix to tensor_split parameter
|
2023-07-14 16:40:53 -04:00 |
|
Andrei Betlen
|
e6c67c8f7d
|
Update llama.cpp
|
2023-07-14 16:40:31 -04:00 |
|
Andrei
|
82b11c8c16
|
Merge pull request #460 from shouyiwang/tensor_split
Add support for llama.cpp's --tensor-split parameter
|
2023-07-14 16:33:54 -04:00 |
|
Shouyi Wang
|
579f526246
|
Resolve merge conflicts
|
2023-07-14 14:37:01 +10:00 |
|
Andrei Betlen
|
6705f9b6c6
|
Bump version
|
2023-07-13 23:32:06 -04:00 |
|
Andrei Betlen
|
de4cc5a233
|
bugfix: pydantic v2 fields
|
2023-07-13 23:25:12 -04:00 |
|
Andrei Betlen
|
896ab7b88a
|
Update llama.cpp
|
2023-07-13 23:24:55 -04:00 |
|
Andrei Betlen
|
7bb0024cd0
|
Fix uvicorn dependency
|
2023-07-12 19:31:43 -04:00 |
|
randoentity
|
3f8f276f9f
|
Add bindings for custom_rope
|
2023-07-10 17:37:46 +02:00 |
|
Andrei Betlen
|
f6c9d17f6b
|
Merge branch 'main' of github.com:abetlen/llama_cpp_python into main
|
2023-07-09 18:20:06 -04:00 |
|
Andrei Betlen
|
8e0f6253db
|
Bump version
|
2023-07-09 18:20:04 -04:00 |
|
Andrei Betlen
|
c988c2ac0b
|
Bump version
|
2023-07-09 18:19:37 -04:00 |
|
Andrei Betlen
|
df3d545938
|
Update changelog
|
2023-07-09 18:13:41 -04:00 |
|
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 Betlen
|
0f3c474a49
|
Bump version
|
2023-07-09 11:44:29 -04:00 |
|
Andrei Betlen
|
9aa64163db
|
Update llama.cpp
|
2023-07-09 11:40:59 -04:00 |
|
Shouyi Wang
|
9f21f548a5
|
Add tensor split
|
2023-07-09 23:00:59 +10:00 |
|
Andrei Betlen
|
99f064e681
|
docker: Add libopenblas to simple image
|
2023-07-09 01:36:39 -04:00 |
|
Andrei Betlen
|
00da643929
|
Update llama.cpp
|
2023-07-08 20:30:34 -04:00 |
|
Andrei Betlen
|
3c85c41573
|
docker: update path to dockerfile
|
2023-07-08 04:04:11 -04:00 |
|
Andrei Betlen
|
1f5e748a7e
|
docker: fix docker build action args
|
2023-07-08 04:00:43 -04:00 |
|
Andrei Betlen
|
9e153fd11d
|
docker: update context path
|
2023-07-08 03:44:51 -04:00 |
|
Andrei Betlen
|
5b7d76608d
|
docker: add checkout action to dockerfile
|
2023-07-08 03:43:17 -04:00 |
|
Andrei Betlen
|
3a2635b9e1
|
Update docker workflow for new simple image
|
2023-07-08 03:37:28 -04:00 |
|
Andrei Betlen
|
670fe4b701
|
Update changelog
|
2023-07-08 03:37:12 -04:00 |
|
Andrei
|
24724202ee
|
Merge pull request #64 from jm12138/add_unlimited_max_tokens
Add unlimited max_tokens
|
2023-07-08 02:38:06 -04:00 |
|
Andrei
|
5d756de314
|
Merge branch 'main' into add_unlimited_max_tokens
|
2023-07-08 02:37:38 -04:00 |
|
Andrei
|
236c4cf442
|
Merge pull request #456 from AgentJ-WR/patch-1
Show how to adjust context window in README.md
|
2023-07-08 02:32:20 -04:00 |
|
Andrei
|
7952ca50c9
|
Merge pull request #452 from audreyfeldroy/update-macos-metal-gpu-step-4
Update macOS Metal GPU step 4
|
2023-07-08 02:32:09 -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 |
|
AgentJ-WR
|
ea4fbadab3
|
Show how to adjust context window in README.md
|
2023-07-07 23:24:57 -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
|
7887376bff
|
Update llama.cpp
|
2023-07-07 19:06:54 -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 |
|
Audrey Roy Greenfeld
|
d270ec231a
|
Update macOS Metal GPU step 4
* Update "today" to version 0.1.62
* Fix numbering (there were 2 step 4's)
|
2023-07-07 11:15:04 +01:00 |
|
Andrei Betlen
|
ca11673061
|
Add universal docker image
|
2023-07-07 03:38:51 -04:00 |
|
Andrei Betlen
|
57d8ec3899
|
Add setting to control request interruption
|
2023-07-07 03:37:23 -04:00 |
|
Andrei Betlen
|
cc542b4452
|
Update llama.cpp
|
2023-07-07 03:04:54 -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 |
|