vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
2138 commits 380 branches 3056 tags 365 MiB
Commit graph

2138 commits

This branch
This branch
All branches
Author SHA1 Message Date
Concedo
2dda63a4eb add tensor split field 2023-09-20 22:46:47 +08:00
Concedo
712b8423f6 class.py changes 2023-09-20 21:27:49 +08:00
Concedo
b63cf223c9 add queue info 2023-09-20 21:07:21 +08:00
Concedo
0eb52cf6c2 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	Makefile
 2023-09-20 21:01:34 +08:00
Concedo
006e87cb56 requirements txt 2023-09-20 21:00:23 +08:00
Concedo
4a0c515da7 rename notepad to classic 2023-09-20 17:51:02 +08:00
Concedo
436cd474cd regex fix 2023-09-20 16:02:19 +08:00
Georgi Gerganov
d119c04c15
examples : fix benchmark-matmult (#1554) 
The precision for Q4_0 has degraded since #1508
 2023-09-20 10:02:39 +03:00
Concedo
2fc91d8727 updated lite 2023-09-20 14:28:55 +08:00
Concedo
c03409c1f6 grammar sampling added for lite 2023-09-19 00:13:30 +08:00
Concedo
0142760fc3 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	Makefile
#	README.md
 2023-09-18 23:20:02 +08:00
Concedo
8c453d1e4e added grammar sampling 2023-09-18 23:02:00 +08:00
Cebtenzzre
8781013ef6
make : restore build-info.h dependency for several targets (#3205) 2023-09-18 10:03:53 -04:00
Concedo
951614bfc6 library unloading is working 2023-09-18 15:03:52 +08:00
Erik Scholz
7ddf185537
ci : switch cudatoolkit install on windows to networked (#3236) 2023-09-18 02:21:47 +02:00
Johannes Gäßler
ee66942d7e
CUDA: fix peer access logic (#3231) 2023-09-17 23:35:20 +02:00
Johannes Gäßler
111163e246
CUDA: enable peer access between devices (#2470) 2023-09-17 16:37:53 +02:00
Concedo
34930bfdc2 updated lite 2023-09-17 20:43:04 +08:00
slaren
8b428c9bc8
llama.cpp : show model size and BPW on load (#3223) 2023-09-17 14:33:28 +02:00
Johannes Gäßler
578d8c8f5c
CUDA: fix scratch malloced on non-main device (#3220) 2023-09-17 14:16:22 +02:00
Concedo
e0fcc9a725 fixed all issues with class.py 2023-09-17 15:23:35 +08:00
IsaacDynamo
b541b4f0b1
Enable BUILD_SHARED_LIBS=ON on all Windows builds (#3215) 2023-09-16 19:35:25 +02:00
Concedo
e107bce105 add another missing field 2023-09-16 23:17:22 +08:00
Concedo
f01a75b563 added missing field 2023-09-16 23:15:44 +08:00
Concedo
733127b160 class.py off by 1 2023-09-16 23:01:12 +08:00
Vlad
5dbc2b3213
Enable build with CUDA 11.0 (make) (#3132) 
* CUDA 11.0 fixes

* Cleaner CUDA/host flags separation

Also renamed GGML_ASSUME into GGML_CUDA_ASSUME
 2023-09-16 16:55:43 +02:00
goerch
b08e75baea
Fixing the last deviations from sentencepiece indicated by test-tokenizer-1 (#3170) 
* Fix für #2721

* Reenable tokenizer test for LLaMa

* Add `console.cpp` dependency

* Fix dependency to `common`

* Fixing wrong fix.

* Make console usage platform specific

Work on compiler warnings.

* Adapting makefile

* Remove trailing whitespace

* Adapting the other parts of the makefile

* Fix typo.

* Fixing the last deviations from sentencepiece indicated by test-tokenizer-1

* Simplify logic

* Add missing change...

* Fix ugly compiler warning

* llama_tokenize should accept strings containing NUL now

* Adding huichen's test case
 2023-09-16 13:41:33 +02:00
Ycros
f6ba36dff6
Reduce warnings. (#439) 2023-09-16 18:52:09 +08:00
Concedo
8d90072a2a updated class.py 2023-09-16 18:22:28 +08:00
Concedo
c96fb3984d Merge branch 'master' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	Makefile
#	examples/quantize/quantize.cpp
#	ggml.c
#	pocs/vdot/vdot.cpp
#	scripts/build-info.cmake
#	scripts/build-info.h.in
#	scripts/build-info.sh
#	tests/test-opt.cpp
#	tests/test-quantize-fns.cpp
#	tests/test-quantize-perf.cpp
#	tests/test-sampling.cpp
 2023-09-16 12:14:19 +08:00
Concedo
53885de6db added multiuser mode 2023-09-16 11:23:39 +08:00
YellowRoseCx
4218641d97
Separate CuBLAS/hipBLAS (#438) 2023-09-16 10:13:44 +08:00
Cebtenzzre
e6616cf0db
examples : add compiler version and target to build info (#2998) 2023-09-15 16:59:49 -04:00
Cebtenzzre
3aefaab9e5
check C++ code with -Wmissing-declarations (#3184) 2023-09-15 15:38:27 -04:00
Cebtenzzre
69eb67e282
fix build numbers by setting fetch-depth=0 (#3197) 2023-09-15 15:18:15 -04:00
Meng Zhang
4fe09dfe66
llama : add support for StarCoder model architectures (#3187) 
* add placeholder of starcoder in gguf / llama.cpp

* support convert starcoder weights to gguf

* convert MQA to MHA

* fix ffn_down name

* add LLM_ARCH_STARCODER to llama.cpp

* set head_count_kv = 1

* load starcoder weight

* add max_position_embeddings

* set n_positions to max_positioin_embeddings

* properly load all starcoder params

* fix head count kv

* fix comments

* fix vram calculation for starcoder

* store mqa directly

* add input embeddings handling

* add TBD

* working in cpu, metal buggy

* cleanup useless code

* metal : fix out-of-bounds access in soft_max kernels

* llama : make starcoder graph build more consistent with others

* refactor: cleanup comments a bit

* add other starcoder models: 3B, 7B, 15B

* support-mqa-directly

* fix: remove max_position_embeddings, use n_train_ctx

* Update llama.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update llama.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* fix: switch to space from tab

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-09-15 22:02:13 +03:00
Cebtenzzre
80291a1d02
common : do not use GNU zero-length __VA_ARGS__ extension (#3195) 2023-09-15 21:02:01 +03:00
Georgi Gerganov
c6f1491da0
metal : fix bug in soft_max kernels (out-of-bounds access) (#3194) 2023-09-15 20:17:24 +03:00
Cebtenzzre
e3d87a6c36
convert : make ftype optional in simple scripts (#3185) 2023-09-15 12:29:02 -04:00
Georgi Gerganov
8c00b7a6ff
sync : ggml (Metal F32 support + reduce ggml-alloc size) (#3192) 
* sync : ggml (Metal F32 support + reduce ggml-alloc size)

ggml-ci

* llama-bench : fix ggml_cpu_has_metal() duplicate function

ggml-ci
 2023-09-15 19:06:03 +03:00
Concedo
63fcbbb3f1 Change label to avoid confusion - rocm hipblas users should obtain binaries from yellowrosecx fork. The rocm support in this repo requires self-compilation 2023-09-16 00:04:11 +08:00
Concedo
8b8eb18567 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	CMakeLists.txt
#	Makefile
#	README.md
#	flake.nix
#	tests/CMakeLists.txt
 2023-09-15 23:51:18 +08:00
Engininja2
7e50d34be6
cmake : fix building shared libs for clang (rocm) on windows (#3176) 2023-09-15 15:24:30 +03:00
Concedo
6b7af55db5 updated lite 2023-09-15 16:44:13 +08:00
Evgeny Kurnevsky
235f7c193b
flake : use pkg-config instead of pkgconfig (#3188) 
pkgconfig is an alias, it got removed from nixpkgs:
295a5e1e2b/pkgs/top-level/aliases.nix (L1408)
 2023-09-15 11:10:22 +03:00
Georgi Gerganov
a51b687657
metal : relax conditions on fast matrix multiplication kernel (#3168) 
* metal : relax conditions on fast matrix multiplication kernel

* metal : revert the concurrnecy change because it was wrong

* llama : remove experimental stuff
 2023-09-15 11:09:24 +03:00
Andrei
76164fe2e6
cmake : fix llama.h location when built outside of root directory (#3179) 2023-09-15 11:07:40 +03:00
Ali Tariq
c2ab6fe661
ci : Cloud-V for RISC-V builds (#3160) 
* Added Cloud-V File

* Replaced Makefile with original one

---------

Co-authored-by: moiz.hussain <moiz.hussain@10xengineers.ai>
 2023-09-15 11:06:56 +03:00
Roland
2d770505a8
llama : remove mtest (#3177) 
* Remove mtest

* remove from common/common.h and examples/main/main.cpp
 2023-09-15 10:28:45 +03:00
Cebtenzzre
98311c4277
llama : make quantize example up to 2.7x faster (#3115) 2023-09-14 21:09:53 -04:00