ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-26 17:20:01 +00:00
Code Issues Packages Projects Releases Wiki Activity
4,143 Commits 672 Branches 1 Tag
ik/sm_graph_cuda_graphs
Commit Graph

4143 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Georgi Gerganov
f48b7628ea 10% performance boost on ARM 2023-03-13 00:56:10 +02:00
Matvey Soloviev
fedc405b41 Fix color getting reset before prompt output done (#65) 
(cherry picked from commit 7eb2987619feee04c40eff69b604017d09919cb6)
 2023-03-13 00:07:34 +02:00
Georgi Gerganov
c240cd1e05 Update README.md 2023-03-12 23:39:01 +02:00
Matvey Soloviev
d35528087e 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
Marc Köhlbrugge
8de246c2d8 Fix typo in README (#45) 2023-03-12 22:30:08 +02:00
Ben Garney
7a708ee9b0 Allow using prompt files (#59) 2023-03-12 22:28:36 +02:00
beiller
c763dc1bc2 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
Sebastián A
fde84afbed 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
Georgi Gerganov
f6f3f1c7c1 Update README.md 2023-03-12 22:09:26 +02:00
Georgi Gerganov
1f0283048a Add CI (#60) 2023-03-12 22:08:24 +02:00
Georgi Gerganov
85c71945cf Revert "weights_only" arg - this causing more trouble than help 2023-03-12 20:59:01 +02:00
Oleksandr Nikitin
a7cf72d75e python/pytorch compat notes (#44) 2023-03-12 14:16:33 +02:00
beiller
a63a748bba 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
Georgi Gerganov
dc91ec5d67 Clarify meaning of hacking 2023-03-12 09:03:25 +02:00
Georgi Gerganov
95fb97b137 README: add "Supported platforms" + update hot topics 2023-03-12 08:41:54 +02:00
deepdiffuser
a9b53a036b 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
Pavol Rusnak
865eff3820 Add LICENSE (#21) 2023-03-12 08:36:03 +02:00
Georgi Gerganov
e34e3e21c4 Update README.md 2023-03-12 01:26:32 +02:00
Juraj Bednar
4cdcd39348 Fix a typo in model name (#16) 2023-03-11 19:32:20 +02:00
Georgi Gerganov
284d9be2de Update README.md 2023-03-11 18:10:18 +02:00
Georgi Gerganov
cc0f26bef3 Add AVX2 support for x86 architectures thanks to @Const-me ! 2023-03-11 18:04:25 +02:00
Georgi Gerganov
bc3184cb2d Fix un-initialized FP16 tables on x86 (#15, #2) 2023-03-11 17:40:14 +02:00
Georgi Gerganov
5afe16962e Bump memory buffer 2023-03-11 12:45:01 +02:00
Georgi Gerganov
35cb0d2a39 Update README.md 2023-03-11 12:31:21 +02:00
Georgi Gerganov
34bb8821d6 .gitignore models/ 2023-03-11 12:27:02 +02:00
Georgi Gerganov
2d2cadab68 Update Makefile var + add comment 2023-03-11 12:27:02 +02:00
Georgi Gerganov
657074b014 Update README.md 2023-03-11 11:34:25 +02:00
Georgi Gerganov
b53c6356f3 Update README.md 2023-03-11 11:34:11 +02:00
Georgi Gerganov
a2799521b9 Support all LLaMA models + change Q4_0 quantization storage 2023-03-11 11:28:30 +02:00
Simon Willison
d4919344b1 Include Python dependencies in README (#6) 2023-03-11 07:47:26 +02:00
Georgi Gerganov
11dae511e3 Update README.md 2023-03-11 01:30:47 +02:00
Georgi Gerganov
240b0bf6ea Update README.md 2023-03-11 01:22:58 +02:00
Georgi Gerganov
87da10c739 Update README.md 2023-03-11 01:18:10 +02:00
Jean-Michaël Celerier
12131a74cb Add missing headers for memcpy and assert (#3) 2023-03-11 01:04:06 +02:00
Georgi Gerganov
01e3d38e1c Update README.md 2023-03-11 00:55:22 +02:00
Georgi Gerganov
8d38e7e279 Update README.md 2023-03-11 00:51:46 +02:00
Georgi Gerganov
586e0f1f3d Update README.md 2023-03-11 00:09:19 +02:00
Georgi Gerganov
4c7f13c170 Update README.md 2023-03-10 23:53:11 +02:00
Georgi Gerganov
8453184bb2 Fix a bug in the rope calculation 2023-03-10 23:46:57 +02:00
Georgi Gerganov
44f3a5b932 Update README.md 2023-03-10 21:52:27 +02:00
Georgi Gerganov
3cda59d04e Final touches 2023-03-10 21:50:46 +02:00
Georgi Gerganov
b2a7bb3e19 Create README.md 2023-03-10 21:47:46 +02:00
Georgi Gerganov
4b5b86d6ee Initial release 2023-03-10 20:56:40 +02:00