vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
1067 commits 380 branches 3056 tags 365 MiB
Commit graph

1067 commits

This branch
This branch
All branches
Author SHA1 Message Date
Howard Su
ca74884f66
opencl : use strstr to check if fp16 supported (#1611) 
* Use strstr to check if fp16 supported

* Ensure ext_buffer is null terminated
 2023-05-28 20:09:56 +03:00
Concedo
28f1196f65 adjust default rep pen range 2023-05-28 19:36:21 +08:00
Concedo
7d159bacd7 updated kobold lite 2023-05-28 11:23:20 +08:00
apcameron
a6704643b6
ggml : add support for the RISCV architecture (#1616) 2023-05-27 23:03:25 +03:00
Concedo
dcc426e2de Merge branch 'master' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
#	Makefile
#	README.md
 2023-05-28 01:08:39 +08:00
Kerfuffle
0df7d63e5b
Include server in releases + other build system cleanups (#1610) 
Set `LLAMA_BUILD_SERVER` in workflow so the `server` example gets build. This currently only applies to Windows builds because it seems like only Windows binary artifacts are included in releases.

Add `server` example target to `Makefile` (still uses `LLAMA_BUILD_SERVER` define and does not build by default)

Fix issue where `vdot` binary wasn't removed when running `make clean`.

Fix compile warnings in `server` example.

Add `.hpp` files to trigger workflow (the server example has one).
 2023-05-27 11:04:14 -06:00
Concedo
5d9f5b28a6 rwkv integration completed 2023-05-28 00:48:56 +08:00
Henri Vasserman
97c9b77c4f
Add documentation about CLBlast (#1604) 
Installing, compiling and using.
 2023-05-27 18:47:55 +03:00
Concedo
55e0fbf024 wip integrating new rwkv 2023-05-27 22:45:28 +08:00
Henri Vasserman
0ecb1bbbeb
[CI] Fix openblas (#1613) 
* Fix OpenBLAS build

* Fix `LLAMA_BLAS_VENDOR` CMake variable that should be a string and not a boolean.
 2023-05-27 17:24:06 +03:00
Georgi Gerganov
93618031c7
ggml : add ggml_tensor_overhead() 2023-05-27 16:19:56 +03:00
Henri Vasserman
83c54e6da5
[CI] CLBlast: Fix directory name (#1606) 2023-05-27 14:18:25 +02:00
Concedo
fe63bfdb0f Revert "allow 2048 blasbatchsize" 
This reverts commit 94dc5c2324.
 2023-05-27 18:13:27 +08:00
0cc4m
97c5cca4e5 OpenCL: Don't load gpu layers into RAM, add mul_f32 kernel 2023-05-27 12:00:56 +02:00
Concedo
94dc5c2324 allow 2048 blasbatchsize 2023-05-27 17:47:18 +08:00
Concedo
92a0d77712 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	CMakeLists.txt
#	Makefile
 2023-05-27 17:44:14 +08:00
Concedo
abfdfb702e added top_a sampler 2023-05-27 17:32:37 +08:00
Georgi Gerganov
bdbda1b17a
ggml : sync ggml core (minor additions, e.g. ggml_get_tensor_by_name()) 2023-05-27 12:23:16 +03:00
0cc4m
ebc5d0651a Use events instead of clFinish, where possible 2023-05-27 10:03:35 +02:00
Concedo
01a0f206df added support for starcoder, which is basically gpt2 2023-05-27 13:35:40 +08:00
Concedo
6d7749c98f no difference 2023-05-27 12:42:19 +08:00
Concedo
bd4fe936f5 cleanup sampling code 2023-05-27 11:58:39 +08:00
Concedo
3c8f404243 integrated token probability viewer in debugmode 2023-05-26 16:40:26 +08:00
Kerfuffle
66874d4fbc
Some improvements to loading the session with --prompt-cache (#1550) 
Improvements to loading the session with `--prompt-cache` in the `main` example.

1. Fix an issue where the `--seed` parameter was ignored when loading a cached prompt.
2. When loading a cached prompt, you previously had to specify the saved prompt (or a prefix of it) again. This pull changes that behavior to default to the prompt that was cached if a prompt wasn't specified by the user.
 2023-05-25 20:18:01 -06:00
Johannes Gäßler
1fcdcc28b1
cuda : performance optimizations (#1530) 
* xor hack

* block y dim

* loop unrolling

* Fixed cmake LLAMA_CUDA_BY option

* Removed hipblas compatibility code

* Define GGML_CUDA_DMMV_BLOCK_Y if not defined

* Fewer iters, more ops per iter

* Renamed DMMV X/Y compilation options
 2023-05-26 00:07:29 +03:00
Concedo
8b8f2f4cf5 up ver to 1.25.1 2023-05-25 14:49:30 +08:00
Concedo
e6eeb234f1 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	README.md
 2023-05-25 10:34:43 +08:00
Concedo
d2da155661 upgraded clblast 2023-05-25 10:18:12 +08:00
Concedo
37a34deaa0 added a second pyinstaller for my own use that uses a different python version. don't use this. 2023-05-24 23:34:11 +08:00
Concedo
bf482d1786 revert klite newline bug, trying to add win7 support 2023-05-24 22:21:01 +08:00
Concedo
844f92688a subpattern fix 2023-05-24 16:48:39 +08:00
Henri Vasserman
ac7876ac20
Update CLBlast to 1.6.0 (#1580) 
* Update CLBlast to 1.6.0
 2023-05-24 10:30:09 +03:00
Concedo
d04b3bbe5e disable mmap when failsafe mode selected from GUI 2023-05-24 15:04:17 +08:00
Evan Jones
c31bbe934b
readme : add docs for chat-persistent.sh (#1568) 
* readme : add docs for chat-persistent.sh

* Update README.md
 2023-05-24 09:24:01 +03:00
Senemu
1359b6aba5
chat-persistent.sh : use bracket expressions in grep (#1564) 2023-05-24 09:16:22 +03:00
Concedo
b314cbfb60 updated lite to support variable streaming lengths 2023-05-24 11:28:35 +08:00
Concedo
c97e10c50c Merge branch 'master' into concedo_experimental 2023-05-24 00:36:30 +08:00
Concedo
abb9ad789c fixed other arch 2023-05-24 00:20:43 +08:00
Maarten ter Huurne
7d873811f3
Fix handling of "invalid property" when creating OpenCL command queue (#1565) 
The `clCreateCommandQueue()` function will return the code
`CL_INVALID_QUEUE_PROPERTIES` when passed unsupported properties,
not `CL_INVALID_PROPERTY` as the original code was checking for.
 2023-05-23 19:01:15 +03:00
Concedo
0c0009e4b4 updated lite 2023-05-23 23:18:52 +08:00
Concedo
355007b019 added sampler seed 2023-05-23 21:52:26 +08:00
Concedo
cd4012c3ed minor fixes to debug logging, fixed a typo, added a new failsafe mode 2023-05-23 21:31:42 +08:00
Concedo
5bf9784381 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	CMakeLists.txt
#	Makefile
#	ggml-opencl.cpp
#	llama.cpp
 2023-05-23 18:19:16 +08:00
0cc4m
2e6cd4b025
OpenCL Token Generation Acceleration (#1459) 
* Move back to C++ for OpenCL

* Refactor OpenCL code to work more like the CUDA code, add missing functions

* Deduplicate dequant kernels

* Add OpenCL compile options

* Use compile args for preprocessing constants

* Restore default platform + device selection by id behavior

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
Co-authored-by: Henri Vasserman <henv@hot.ee>
 2023-05-23 00:33:24 +03:00
Concedo
7894e85788 fixed a bug in previous klite 2023-05-22 21:54:24 +08:00
Concedo
a05da31fe7 updated embedded lite 2023-05-22 20:58:54 +08:00
Concedo
e20e302e87 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	CMakeLists.txt
#	Makefile
 2023-05-22 17:05:34 +08:00
Concedo
b9f06a7670 mavx only for windows by default, let them eat march native. 2023-05-22 16:48:55 +08:00
Concedo
981d5ba866 Merge remote-tracking branch 'occam/opencl-dev' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
#	Makefile
#	README.md
#	ggml-opencl.cpp
#	llama.cpp
#	otherarch/ggml_v2-opencl-legacy.c
 2023-05-22 16:16:48 +08:00
Concedo
169a26d15f removed unused build targets 2023-05-22 13:53:10 +08:00