Commit Graph

1180 Commits

Author SHA1 Message Date
Georgi Gerganov
35938ee3b0
llama : update logic for number of threads when using BLAS 2023-09-05 10:46:39 +03:00
Georgi Gerganov
921772104b
speculative : add grammar support (#2991)
* speculative : add grammar support

* grammars : add json_arr.gbnf

* grammar : add comments to new grammar file

* grammar : remove one nested level

* common : warm-up with 2 tokens - seems to work better

* speculative : print draft token pieces

* speculative : reuse grammar parser + better logs and comments

* speculative : avoid grammar_mem

* make : fix speculative build
2023-09-05 08:46:17 +03:00
Georgi Gerganov
2ba85c8609
py : minor 2023-09-04 22:50:50 +03:00
Georgi Gerganov
e36ecdccc8
build : on Mac OS enable Metal by default (#2901)
* build : on Mac OS enable Metal by default

* make : try to fix build on Linux

* make : move targets back to the top

* make : fix target clean

* llama : enable GPU inference by default with Metal

* llama : fix vocab_only logic when GPU is enabled

* common : better `n_gpu_layers` assignment

* readme : update Metal instructions

* make : fix merge conflict remnants

* gitignore : metal
2023-09-04 22:26:24 +03:00
slaren
bd33e5ab92
ggml-opencl : store GPU buffer in ggml_tensor::extra (#2994) 2023-09-04 14:59:52 +02:00
Cebtenzzre
3103568144
llama-bench : make cpp file non-executable (#2999) 2023-09-04 13:40:18 +03:00
Leng Yue
5b8530d88c
make : add speculative example (#3003) 2023-09-04 13:39:57 +03:00
Aarni Koskela
e4386f417f
server : add a subtle loading animation to the edit box (#2466)
* editorconfig: add override for the server HTML (which already is 2-space indented)

* server: add a subtle loading animation to the edit box
2023-09-04 16:28:55 +08:00
Jiahao Li
35195689cd
2x faster (rms) norm cuda kernels (3.7% e2e improvement) (#2985)
* 2x faster (rms) norm cuda kernels

* Fix code style
2023-09-04 08:53:30 +02:00
slaren
cf9b08485c
ggml-alloc : use virtual memory for measurement (#2973)
* ggml-alloc : use virtual memory for measurement

* compatibility fixes for MAP_ANONYMOUS

* fallback to fixed address for systems without virtual memory
2023-09-03 20:34:09 +02:00
Georgi Gerganov
47068e5170
speculative : PoC for speeding-up inference via speculative sampling (#2926)
* speculative : initial example

* speculative : print encoding speed

* speculative : add --draft CLI arg
2023-09-03 15:12:08 +03:00
Georgi Gerganov
8f429fa511
perplexity : fix ETA by warming up the model with an empty run 2023-09-03 13:43:17 +03:00
Kerfuffle
6519e9c99c
gguf(python): Fix special vocab handling when id < 0 (#2984) 2023-09-03 04:38:43 -06:00
Georgi Gerganov
b7f2aa9e51
metal : restore 363f0bf and fix reduce in F16_F32 kernels (#2986) 2023-09-03 13:23:33 +03:00
Alon
73a12a6344
cov : disable comment in PRs (#2989) 2023-09-03 13:19:01 +03:00
opparco
3730134776
llama : fix bpe tokenize from byte (#2889) 2023-09-03 13:18:09 +03:00
Georgi Gerganov
d9151e6f57
metal : revert 6af0bab until we fix it
This restores the generated text to be the same as before #2959
2023-09-03 12:40:56 +03:00
Alon
afc43d5f82
cov : add Code Coverage and codecov.io integration (#2928)
* update .gitignore

* makefile: add coverage support (lcov, gcovr)

* add code-coverage workflow

* update code coverage workflow

* wun on ubuntu 20.04

* use gcc-8

* check why the job hang

* add env vars

* add LLAMA_CODE_COVERAGE=1 again

* - add CODECOV_TOKEN
- add missing make lcov-report

* install lcov

* update make file -pb flag

* remove unused  GGML_NITER from workflows

* wrap coverage output files in COV_TARGETS
2023-09-03 11:48:49 +03:00
Wentai Zhang
6460f758db
opencl : fix a bug in ggml_cl_pool_malloc() for ggml_cl_mul_mat_f32() (#2955)
Co-authored-by: Wentai Zhang <wentaizhang@tencent.com>
2023-09-03 11:46:44 +03:00
Kawrakow
ca82cf7bac
metal : more optimizations (#2959)
* Very minor speedup via simd-group synchronization in f16 x f32

* Another very minor speedup on metal

* Quite significant PP speedup on metal

* Another attempt

* Minor

* Massive improvement for TG for fp16

* ~4-5% improvement for Q8_0 TG on metal

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-09-03 11:06:22 +03:00
kchro3
6a31a3bd98
swift : add support for k-quants (#2983) 2023-09-03 09:21:05 +03:00
Kerfuffle
cff7b0bf07
convert.py : BPE fixes (#2938)
* convert.py: BPE fixes?

* Remove unnecessary conditional in addl token error handling
2023-09-03 08:52:13 +03:00
Ido S
340af42f09
docs : add catai to README.md (#2967) 2023-09-03 08:50:51 +03:00
momonga
c42f0ec6b3
examples : fix gpt-neox (#2943)
Co-authored-by: mmnga <mmnga1mmnga@gmail.com>
2023-09-03 08:36:28 +03:00
kchro3
2753415afd
swift : add missing c file to Package.swift (#2978) 2023-09-03 08:27:25 +03:00
Cebtenzzre
bc054af97a
make : support overriding CFLAGS/CXXFLAGS/CPPFLAGS/LDFLAGS (#2886)
* make : remove unused -DGGML_BIG_ENDIAN

* make : put preprocessor stuff in CPPFLAGS

* make : pass Raspberry Pi arch flags to g++ as well

* make : support overriding CFLAGS/CXXFLAGS/CPPFLAGS/LDFLAGS

* make : fix inverted conditional
2023-09-03 08:26:59 +03:00
Kerfuffle
3358c381f6
logging: Fix creating empty file even when disabled (#2966)
* logging: Fix creating empty file even when disabled

* Minor formatting fix

Co-authored-by: staviq <staviq@gmail.com>

---------

Co-authored-by: staviq <staviq@gmail.com>
2023-09-02 11:53:55 -06:00
bandoti
52315a4216
readme : update clblast instructions (#2903)
* Update Windows CLBlast instructions

* Update Windows CLBlast instructions

* Remove trailing whitespace
2023-09-02 15:53:18 +03:00
Karsten Weiss
8b56b4f2c3
metal : show all Metal device instances in the system (#2952)
* ggml_metal_init: Show all Metal device instances in the system

Also show the default Metal device that was picked.

* Update ggml-metal.m

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-09-02 15:29:09 +03:00
Jhen-Jie Hong
21f3d1be86
k-quants : fix build on armv7 (android only) (#2920)
* k-quants : fix build on armv7

* ggml : cleanup unused arm32 specific impl

* k-quants : avoid some unused vzero / mzero define

* ggml-alloc : use 4g for MEASURE_MAX_SIZE in 32-bit arm
2023-09-02 15:23:45 +03:00
Jhen-Jie Hong
571083f508
server : avoid aniprompt in probabilities of final response (#2849) 2023-09-02 08:31:46 +08:00
Engininja2
f04d002844
cuda : vsubss4 for older versions of ROCm/clang (#2942) 2023-09-01 23:33:19 +02:00
ZHAOKAI WANG
69fdbb9abc
readme : quick start command fix (#2908)
* quick start command fix

* quick start win command fix
2023-09-01 17:06:44 +03:00
Kerfuffle
5d6f19f16b
Allow quantize to only copy tensors, some other improvements (#2931)
* Allow quantize tool to only copy tensors to allow repackaging models.

* Slightly better logic when requantizing.

* Change help message to go to `stdout`.
2023-09-01 08:02:48 -06:00
Georgi Gerganov
0d58936686
llama2c : rename function 2023-09-01 17:01:11 +03:00
Cebtenzzre
6c9c23429b
make : use unaligned vector moves on MinGW (#2945)
Fixes #2922
2023-09-01 16:53:14 +03:00
m3ndax
ee8654bcd0
minor : add const qualifiers (#2853)
* made the methods const

# Conflicts:
#	examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp

* made method const

* Update convert-llama2c-to-ggml.cpp

removed write_raw and write_u32

* llama2c : remove misleading const

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-09-01 16:47:27 +03:00
Konstantin Herud
49bb9cbe0f
docs : add java-llama.cpp to README.md (#2935) 2023-09-01 16:36:14 +03:00
Cebtenzzre
ef15649972
build : fix most gcc and clang warnings (#2861)
* fix most gcc and clang warnings

* baby-llama : remove commented opt_params_adam

* fix some MinGW warnings

* fix more MinGW warnings
2023-09-01 16:34:50 +03:00
Ben Siraphob
d8d6977f48
examples : add C grammar (#2357) 2023-09-01 16:32:14 +03:00
Tameem
5aec2cfaac
ggml : add RISC-V vector intrinsics support (#2929)
* added support for RISCV CFLAGS & native compile + cross compile options

* Add RISC-V Vector Intrinsics Support

Added RVV intrinsics for following
   ggml_vec_dot_q4_0_q8_0
   ggml_vec_dot_q4_1_q8_1
   ggml_vec_dot_q5_0_q8_0
   ggml_vec_dot_q5_1_q8_1
   ggml_vec_dot_q8_0_q8_0

Co-authored-by: Sharafat <sharafat.hussain@10xengineers.ai>
Signed-off-by: Ahmad Tameem <ahmad.tameem@10xengineers.ai>

---------

Signed-off-by: Ahmad Tameem <ahmad.tameem@10xengineers.ai>
Co-authored-by: moiz.hussain <moiz.hussain@10xengineers.ai>
Co-authored-by: Sharafat <sharafat.hussain@10xengineers.ai>
2023-09-01 16:27:40 +03:00
Georgi Gerganov
13268c5331
metal : slight speed-up for add and mul kernels (#2917) 2023-09-01 13:42:41 +03:00
staviq
4dcd47d71d
logs : fix mingw-like builds (fixes #2898) (#2911)
* fix mingw-like builds

* formatting

* make LOG_COMPAT easier to override and extend

* simplify win detection

* fix for #2940
2023-09-01 12:07:06 +03:00
Cebtenzzre
18705a30ef
llama2c : fix segfault and alloc-dealloc-mismatch (#2913)
* llama2c : fix segfault if vocab is not found

* llama2c : fix mismatch between new[] and delete

* llama2c : fix basename on Windows

* llama2c : use a destructor to prevent memory leaks
2023-09-01 12:03:49 +03:00
Kawrakow
e8d9158925
metal: somewhat faster f16 x f32 matrix multiply kernel (#2951)
* Somewhat faster f16 x f32 matrix multiply kernel

* Better use 32 thread groups for f16 x f32

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-09-01 11:15:57 +03:00
Cebtenzzre
bce1fef328
convert : fix another python 3.8 issue (#2949) 2023-08-31 22:13:51 -04:00
slaren
528134dd02
remove convert-llama-7b-pth-to-gguf.py and convert-llama-hf-to-gguf.py (#2906) 2023-09-01 01:32:09 +02:00
Kerfuffle
aeefac4ff7
scripts: Use local gguf package when running from repo (#2927)
* scripts: Use local gguf when running from repo
2023-08-31 16:49:24 -06:00
DannyDaemonic
e8422de39e
@vxiiduu's fix for PrefetchVirtualMemory (#2930)
Reimplement fix for `PrefetchVirtualMemory`.
Co-authored-by: vxiiduu <73044267+vxiiduu@users.noreply.github.com>
2023-08-31 04:21:45 -07:00
Cebtenzzre
92d0b751a7
convert : fix python 3.8 support, modernize type annotations (#2916)
* convert : fix python 3.8 support

* convert : sort imports

* convert : fix required parameters in convert-llama-ggmlv3-to-gguf

* convert : fix mypy errors in convert-llama-ggmlv3-to-gguf

* convert : use PEP 585 generics and PEP 604 unions

Now that we have `from __future__ import annotations`, we can use this
modern syntax in Python 3.7 instead of restricting support to Python 3.9
or 3.10 respectively.

* gguf.py : a tuple is already a tuple

* add mypy.ini

* convert : add necessary `type: ignore` comments

* gguf-py: bump version
2023-08-31 08:02:23 +03:00