47857e564c
Don't use vdotq_s32 if it's not available ( #139 )
...
* Don't use vdotq_s32 if it's not available
`dotprod` extensions aren't available on some ARM CPUs (e.g. Raspberry Pi 4), so check for them and only use them if they're available.
Reintroduces the code removed in 84d9015ggerganov@gmail.com >
2023-03-14 21:34:37 +02:00
60f819a2b1
Add section to README on how to run the project on Android ( #130 )
2023-03-14 15:30:08 +02:00
97ab2b2578
Add Misc section + update hot topics + minor fixes
2023-03-14 09:43:52 +02:00
2f700a2738
Add windows to the CI ( #98 )
2023-03-13 22:29:10 +02:00
c09a9cfb06
CMake build in Release by default ( #75 )
2023-03-13 21:22:15 +02:00
7ec903d3c1
Update contribution section, hot topics, limitations, etc.
2023-03-13 19:21:51 +02:00
4497ad819c
Print system information
2023-03-13 19:15:08 +02:00
ed6849cc07
Initial support for CMake ( #75 )
2023-03-13 19:12:33 +02:00
41be0a3b3d
Add NetBSD support. ( #90 )
2023-03-13 18:40:54 +02:00
671d5cac15
Use fprintf for diagnostic output ( #48 )
...
keep printf only for printing model output
one can now use ./main ... 2>dev/null to suppress any diagnostic output
2023-03-13 18:39:56 +02:00
84d9015c4a
Use vdotq_s32 to improve performance ( #67 )
...
* 10% performance boost on ARM
* Back to original change
2023-03-13 18:36:44 +02:00
63fd76fbb0
Reduce model loading time ( #43 )
...
* Use buffering
* Use vector
* Minor
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2023-03-13 18:33:43 +02:00
2a20f48efa
Fix UTF-8 handling (including colors) ( #79 )
2023-03-13 18:24:18 +02:00
d1f224712d
Add quantize script for batch quantization ( #92 )
...
* Add quantize script for batch quantization
* Indentation
* README for new quantize.sh
* Fix script name
* Fix file list on Mac OS
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2023-03-13 18:15:20 +02:00
1808ee0500
Add initial contribution guidelines
2023-03-13 09:42:26 +02:00
a169bb889c
Gate signal support on being on a unixoid system. ( #74 )
2023-03-13 04:08:01 +01:00
460c482540
Fix token count accounting
2023-03-13 01:04:41 +01:00
c80e2a8f2a
Revert "10% performance boost on ARM"
...
This reverts commit 113a9e83eb
2023-03-13 01:28:08 +02:00
54a0e66ea0
Check for vdotq_s32 availability
2023-03-13 01:21:03 +02:00
543c57e991
Ammend to previous commit - forgot to update non-QRDMX branch
2023-03-13 01:05:24 +02:00
113a9e83eb
10% performance boost on ARM
2023-03-13 00:56:10 +02:00
404fac0d62
Fix color getting reset before prompt output done ( #65 )
...
(cherry picked from commit 7eb2987619feee04c40eff69b604017d09919cb6)
2023-03-13 00:07:34 +02:00
1a0a74300f
Update README.md
2023-03-12 23:39:01 +02:00
96ea727f47
Add interactive mode ( #61 )
...
* Initial work on interactive mode.
* Improve interactive mode. Make rev. prompt optional.
* Update README to explain interactive mode.
* Fix OS X build
2023-03-12 23:13:28 +02:00
9661954835
Fix typo in README ( #45 )
2023-03-12 22:30:08 +02:00
f385f8dee8
Allow using prompt files ( #59 )
2023-03-12 22:28:36 +02:00
02f0c6fe7f
Add back top_k ( #56 )
...
* Add back top_k
* Update utils.cpp
* Update utils.h
---------
Co-authored-by: Bill Hamilton <bill.hamilton@shopify.com >
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2023-03-12 22:23:15 +02:00
eb062bb012
Windows fixes ( #31 )
...
* Apply fixes suggested to build on windows
Issue: https://github.com/ggerganov/llama.cpp/issues/22
* Remove unsupported VLAs
* MSVC: Remove features that are only available on MSVC C++20.
* Fix zero initialization of the other fields.
* Change the use of vector for stack allocations.
2023-03-12 22:15:00 +02:00
7027a97837
Update README.md
2023-03-12 22:09:26 +02:00
2d555e5b42
Add CI ( #60 )
2023-03-12 22:08:24 +02:00
7c9e54e55e
Revert "weights_only" arg - this causing more trouble than help
2023-03-12 20:59:01 +02:00
b9bd1d0141
python/pytorch compat notes ( #44 )
2023-03-12 14:16:33 +02:00
129c7d1ea8
Add repetition penalty ( #20 )
...
* Adding repeat penalization
* Update utils.h
* Update utils.cpp
* Numeric fix
Should probably still scale by temp even if penalized
* Update comments, more proper application
I see that numbers can go negative so a fix from a referenced commit
* Minor formatting
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2023-03-12 11:27:42 +02:00
702fddf5c5
Clarify meaning of hacking
2023-03-12 09:03:25 +02:00
7d86e25bf6
README: add "Supported platforms" + update hot topics
2023-03-12 08:41:54 +02:00
a93120236f
use weights_only in conversion script ( #32 )
...
this restricts malicious weights from executing arbitrary code by restricting the unpickler to only loading tensors, primitive types, and dictionaries
2023-03-12 08:36:35 +02:00
6a9a67f0be
Add LICENSE ( #21 )
2023-03-12 08:36:03 +02:00
da1a4ff01f
Update README.md
2023-03-12 01:26:32 +02:00
6b2cb6302f
Fix a typo in model name ( #16 )
2023-03-11 19:32:20 +02:00
4235e3d5b3
Update README.md
2023-03-11 18:10:18 +02:00
f1eaff4721
Add AVX2 support for x86 architectures thanks to @Const-me !
2023-03-11 18:04:25 +02:00
a9e58529ea
Fix un-initialized FP16 tables on x86 ( #15 , #2 )
2023-03-11 17:40:14 +02:00
7d9ed7b25f
Bump memory buffer
2023-03-11 12:45:01 +02:00
0c6803321c
Update README.md
2023-03-11 12:31:21 +02:00
f60fa9e50a
.gitignore models/
2023-03-11 12:27:02 +02:00
7211862c94
Update Makefile var + add comment
2023-03-11 12:27:02 +02:00
a5c5ae2f54
Update README.md
2023-03-11 11:34:25 +02:00
ea977e85ec
Update README.md
2023-03-11 11:34:11 +02:00
007a8f6f45
Support all LLaMA models + change Q4_0 quantization storage
2023-03-11 11:28:30 +02:00
5f2f970d51
Include Python dependencies in README ( #6 )
2023-03-11 07:47:26 +02:00
