vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
1607 commits 380 branches 3056 tags 365 MiB
Commit graph

1607 commits

This branch
This branch
All branches
Author SHA1 Message Date
Concedo
993ba3b026 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	README.md
 2023-07-24 11:59:00 +08:00
Concedo
280abaf029 added stop reason in the perf endpoint 2023-07-24 11:55:35 +08:00
Kawrakow
2f9cf974a0
Some more Q4_K and Q5_K speedup on CUDA (#2346) 
* Faster Q5_K on CUDA

* Small Q5_K improvement on older GPUs

* Spped up Q4_K on CUDA

GTX1660: 29.5 ms/t -> 25.6 ms/t
RTX4080: 8.40 ms/t -> 8.25 ms/t

* Spped up Q4_K on CUDA

GTX1660: 36.7 ms/t -> 35.6 ms/t
RTX4080:  9.8 ms/t ->  9.5 ms/t

* Address PR comments

* Add some comments to satisfy PR reviewer

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2023-07-24 00:19:47 +03:00
IgnacioFDM
4f06592cc6
Add gqa parameter support to the server (#2351) 
* Add gqa parameter support to the server
* Change help from stderr to stdout
 2023-07-23 23:31:17 +03:00
Johannes Gäßler
70d26ac388
Fix __dp4a documentation (#2348) 2023-07-23 17:49:06 +02:00
Concedo
910744e2c0 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	Makefile
#	README.md
#	flake.nix
#	llama.cpp
 2023-07-23 22:37:38 +08:00
Concedo
c28ab4e1b7 update lite, try support k80 2023-07-23 21:50:35 +08:00
wzy
57921ca6db
common : n_threads == -1 uses std:🧵:hardware_concurrency() (#2347) 
* Fix #2345, fix incorrect n_threads

* Update examples/common.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-07-23 16:33:02 +03:00
slaren
3602ac4255
fix n_tasks (#2342) 
ggml-ci
 2023-07-23 15:19:39 +02:00
slaren
95a6c595e7
ggml: move op parameters from tensors to ggml_tensor::op_params (#2333) 
* ggml: move op parameters from tensors to ggml_tensor::op_params

* alibi: use memcpy for float params

* remove `src[1] = NULL` in ops
 2023-07-23 14:36:02 +02:00
Georgi Gerganov
e76d630df1
llama : grouped-query attention + LLaMAv2 70B support (#2276) 
* CUDA: GQA implementation

* llama : support for GQA and LLaMAv2 70B

ggml-ci

* py : fix hparams parsing (if-else blocks)

ggml-ci

* py : oh boy ..

ggml-ci

* help : fix gqa value for 70B

ggml-ci

---------

Co-authored-by: JohannesGaessler <johannesg@5d6.de>
 2023-07-23 15:09:47 +03:00
maddes8cht
1d0824b247
llama : print help to stdout (#2338) 2023-07-23 14:59:48 +03:00
wzy
bc3ec2cdc9
flake : support nix build '.#opencl' (#2337) 2023-07-23 14:57:02 +03:00
Christian Demsar
a940458e48
llama : print max tensor size to stderr (#2336) 2023-07-23 14:56:34 +03:00
Jose Maldonado
91171b8072
make : fix CLBLAST compile support in FreeBSD (#2331) 
* Fix Makefile for CLBLAST compile support and instructions for compile llama.cpp FreeBSD

* More general use-case for CLBLAST support (Linux and FreeBSD)
 2023-07-23 14:52:08 +03:00
AustinMroz
355c80f49e
examples : simplify vim plugin (#2327) 
Uses builtin json_encode and json_decode functions to simplify escaping
Removes the need for temp files
 2023-07-23 14:16:48 +03:00
Jiahao Li
83a00ce69b
metal : support bcast add & dup & cont op (#2323) 2023-07-23 14:00:37 +03:00
Concedo
2e84eac7f6 Merge branch 'master' into concedo_experimental 2023-07-23 16:23:00 +08:00
Concedo
aa05eadb6f Merge branch 'master' into concedo_experimental 
# Conflicts:
#	llama.cpp
 2023-07-23 16:22:44 +08:00
Kawrakow
d2a43664f9
Speed up Q4_K (#2322) 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2023-07-23 08:49:20 +03:00
Concedo
1108232e30 Merge branch 'concedo' into concedo_experimental 2023-07-23 09:59:58 +08:00
Concedo
0cca0726fe reduce number of retries, fixed maxlength > maxctx bug 2023-07-23 09:59:34 +08:00
Ycros
56995caa48
Fix mirostatv2. (#338) 2023-07-23 09:52:03 +08:00
Johannes Gäßler
b9b7d94fc1
CUDA: Fixed 7b q3_K_S with mul_mat_vec_q (#2313) 2023-07-22 21:27:34 +02:00
Georgi Gerganov
b47b8a9cfe
llama : optimize memory buffers (#2325) 2023-07-22 21:17:57 +03:00
Concedo
fa0270df7c added some checks to skip generation if busy 2023-07-22 23:10:04 +08:00
Concedo
2807d98fd4 touchup (+2 squashed commit) 
Squashed commit:

[8b06458] fixed broken param order

[7eabdc0] very broken, do not use
 2023-07-22 22:57:56 +08:00
klosax
b5fe67f8c6
Perplexity: Compute scores correlated to HellaSwag (#2312) 
* Add parameter --perplexity-lines to perplexity.cpp
 2023-07-22 14:21:24 +02:00
whoreson
24baa54ac1
examples : basic VIM plugin 
VIM plugin for server exe
 2023-07-22 13:34:51 +03:00
Concedo
3aec3038d4 bump scratch buffers 2023-07-22 18:12:18 +08:00
Georgi Gerganov
dd6c67d3cb
ci : fix args 2023-07-22 12:00:56 +03:00
Georgi Gerganov
5d500e8ccf
ci : add 7B CUDA tests (#2319) 
* ci : add 7B CUDA tests

ggml-ci

* ci : add Q2_K to the tests

* ci : bump CUDA ppl chunks

ggml-ci

* ci : increase CUDA TG len + add --ignore-eos

* ci : reduce CUDA ppl cunks down to 4 to save time
 2023-07-22 11:48:22 +03:00
Concedo
52c5856a08 auto populate horde model name 2023-07-22 16:03:12 +08:00
Concedo
dd3f8dabed updated cluster to horde.koboldai.net 2023-07-22 12:42:40 +08:00
Concedo
236d0e8955 add tip about using other workers 2023-07-22 12:29:22 +08:00
Concedo
701bf0a6cd reduce sleep time between jobs 2023-07-22 11:56:43 +08:00
Concedo
343ae756fa Merge branch 'master' into concedo_experimental 
# Conflicts:
#	.gitignore
#	CMakeLists.txt
#	Makefile
#	README.md
#	flake.nix
#	ggml-cuda.cu
 2023-07-22 11:51:30 +08:00
Concedo
52c98228aa bugfixes for missing params 2023-07-22 11:37:44 +08:00
Concedo
d7ab6adbc1 embedded horde worker is ready 2023-07-22 11:21:32 +08:00
Richard Roberson
7d5f18468c
examples : add easy python script to create quantized (k-bit support) GGML models from local HF Transformer models (#2311) 
* Resync my fork with new llama.cpp commits

* examples : rename to use dash instead of underscore

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-07-21 22:01:10 +03:00
Concedo
75064b4ada wip on embedded horde worker 2023-07-22 01:30:25 +08:00
Kawrakow
d924522a46
Custom RoPE + bettter memory management for CUDA (#2295) 
* Custom RoPE + bettter memory management for CUDA

* Adjusted look ahead in ggml_cuda_pool_malloc to 5%

This is sufficient it seems.
We end up using about 200 MB less VRAM that way when running
the 13B model with context 8192.

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2023-07-21 17:27:51 +03:00
Kawrakow
4d76a5f49b
Faster Q3_K implementation on Metal (#2307) 
* Faster Q3_K on Metal

* Additional Q3_K speedup on Metal

* Q3_K for QK_K = 64

* Better Q3_K for QK_K = 64

21.6 ms/t -> 21.1 ms/t

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2023-07-21 17:05:30 +03:00
Georgi Gerganov
0db14fef06
ggml : fix the rope fix (513f861953) 2023-07-21 15:16:55 +03:00
Ikko Eltociear Ashimine
03e566977b
examples : fix typo in minigpt4.py (#2298) 
promt -> prompt
 2023-07-21 14:53:07 +03:00
Georgi Gerganov
513f861953
ggml : fix rope args order + assert (#2054) 2023-07-21 14:51:34 +03:00
Georgi Gerganov
3973b25a64
gitignore : fix final newline 2023-07-21 14:42:41 +03:00
Guillaume "Vermeille" Sanchez
ab0e26bdfb
llama : remove cfg smooth factor as it is only a reparameterization of the guidance scale (#2280) 2023-07-21 13:58:36 +03:00
Jose Maldonado
73643f5fb1
gitignore : changes for Poetry users + chat examples (#2284) 
A fix in Makefile for FreeBSD users. In the platfrom x86_64 is amd64. This fix resolve compilation using CFLAGS and CXXFLAGS with -march=native and -mtune=native
Add two examples for interactive mode using Llama2 models (thx TheBloke for models)

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-07-21 13:53:27 +03:00
Georgi Gerganov
a814d04f81
make : fix indentation 2023-07-21 13:50:55 +03:00