vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
1701 commits 380 branches 3056 tags 365 MiB
Commit graph

1701 commits

This branch
This branch
All branches
Author SHA1 Message Date
Concedo
b40550cf1a change wiki link 2023-07-28 13:01:12 +08:00
Concedo
31486ebc8d updated readme 2023-07-28 11:32:55 +08:00
niansa/tuxifan
edcc7ae7d2
Obtaining LLaMA 2 instructions (#2308) 
* Obtaining LLaMA 2 instructions

* Removed sharing warning for LLaMA 2

* Linked TheBloke's GGML repos

* Add LLaMA 2 to list of supported models

* Added LLaMA 2 usage instructions

* Added links to LLaMA 2 70B models
 2023-07-28 03:14:11 +02:00
mj-shifu
7c529cede6
convert.py : Update to support 70B HF format model files (#2427) 
* convert.py : fix llama 2 70b conversion from Huggingface
 2023-07-27 14:39:17 -06:00
Georgi Gerganov
1a941869cb
metal : disable graph concurrency optimization due to bug (#2413) 2023-07-27 11:00:54 +03:00
slaren
b5472ea0ad
ggml : fix assert in ggml_set_unary_op (#2410) 2023-07-26 23:57:23 +02:00
Cebtenzzre
6df1f5940f
make : build with -Wmissing-prototypes (#2394) 2023-07-26 21:00:04 +03:00
slaren
5488fb789e
ggml : allocate graphs in a context (#2392) 
* ggml : graph allocation in contexts

* allocate work buffer as a ggml_object in ggml_graph_compute_with_ctx

* llama.cpp : allocate graph in the context

* add GGML_PAD

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-07-26 15:56:53 +02:00
Concedo
94e0a06daf updated lite, up ver (+1 squashed commits) 
Squashed commits:

[7d6520f] updated lite, up ver
 2023-07-26 11:03:17 +08:00
Concedo
b184380aae Revert "a better default rms_norm_eps" 
This reverts commit 0c26799e77.
 2023-07-26 10:23:45 +08:00
Concedo
f53d2aabb4 Merge branch 'master' into concedo_experimental 2023-07-26 10:19:59 +08:00
Kawrakow
eb542d3932
Add LLAMA_DEFAULT_RMS_EPS so we can change the default (#2384) 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2023-07-25 18:35:53 +03:00
Concedo
6a054b80b0 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	scripts/build-info.sh
 2023-07-25 22:55:55 +08:00
Concedo
0c26799e77 a better default rms_norm_eps 2023-07-25 22:51:01 +08:00
slaren
07aaa0f63f
ggml : fix ggml_flash_attn to use op_params (#2387) 
* ggml : fix ggml_flash_attn to use op_params
 2023-07-25 16:20:12 +02:00
ldwang
fce48caf9a
convert.py : support bpe tokenizer (#2228) 
* support bpe tokenizer in convert

Signed-off-by: ldwang <ftgreat@gmail.com>

* support bpe tokenizer in convert

Signed-off-by: ldwang <ftgreat@gmail.com>

* support bpe tokenizer in convert, fix

Signed-off-by: ldwang <ftgreat@gmail.com>

---------

Signed-off-by: ldwang <ftgreat@gmail.com>
Co-authored-by: ldwang <ftgreat@gmail.com>
 2023-07-25 16:22:09 +03:00
Jiahao Li
875086bdb9
ggml : relax contiguous constraints in activation function (#2371) 2023-07-25 15:58:32 +03:00
slaren
da1889834a
ggml : improve graph build time via hash table lookup (#2329) 
* improve graph build time

* ggml_tensor : use 1 bit per flag

* use a hash table instead
 2023-07-25 15:32:20 +03:00
Hesen Peng
82552b7f54
build : fix line breaking error in build-info.sh (#2349) 
* fix line breaking

* build number line break removal
 2023-07-25 15:24:09 +03:00
Xiao-Yong Jin
0c06204fb3
main : add --in-prefix-bos to prefix BOS to user inputs; keep EOS (#2304) 
* add `--in-prefix-bos` to prefix BOS to user inputs; keep EOS

The BOS precedes the string specified by `--in-prefix`.
Model generated EOS is now kept in the context.

It provides a way to strictly following the prompt format used in
Llama-2-chat.

The EOS handling also benefits some existing finetunes that uses
EOS to mark the end of turn.

* examples/common: move input_prefix_bos to other bools
 2023-07-25 15:19:11 +03:00
Eve
1fed755b1f
ci : add non-AVX scalar build/test (#2356) 
* noavx build and test

* we don't need to remove f16c in windows
 2023-07-25 15:16:13 +03:00
katsu560
be2301bcda
k_quants : add AVX support to dot functions with QK_K as 64 (#2339) 
* add AVX to ggml_vec_dot_q2_K_q8_K()

* add AVX to ggml_vec_dot_q3_K_q8_K()

* add AVX to ggml_vec_dot_q4_K_q8_K()

* add AVX to ggml_vec_dot_q5_K_q8_K()

* add AVX to ggml_vec_dot_q6_K_q8_K()

* refactor AVX code in ggml_vec_dot_q6_K_q8_K()
 2023-07-25 15:13:41 +03:00
Shouzheng Liu
1aa18ef994
metal : concurrently dispatch commands (#2358) 
* metal: concurrently dispatch commands

Function `ggml_metal_graph_find_concurrency` will run and write
commands that can be issued concurrently to metal context `concur_list`
array, when `ggml_metal_graph_compute` is called for the first time.

* metal: don't call find_concurrency automatically.

* metal : code style changes

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-07-25 15:00:19 +03:00
Concedo
3e68cdd26a Merge branch 'master' into concedo_experimental 
# Conflicts:
#	Makefile
#	tests/test-grad0.c
 2023-07-25 18:52:48 +08:00
Kawrakow
9a08eaf3c4
Another speed gain for Q4_0 and Q4_1 on Metal (#2375) 
* Another speed gain for Q4_0 and Q4_1 on Metal

* Have N_DST, etc., be template parameters

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2023-07-25 13:48:29 +03:00
Kawrakow
129d844c87
Fix Q4_K and Q5_K for QK_K = 64 on CUDA (#2359) 
* Fix Q4_K and Q5_K for QK_K = 64

* Very slightly better Q5_K bit fiddling

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2023-07-25 13:48:04 +03:00
Concedo
66e4b5141e fix horde worker host and client agent 2023-07-25 18:18:41 +08:00
slaren
d5512b782b
server: add rms_norm_eps parameter (#2380) 2023-07-25 12:36:17 +03:00
Henri Vasserman
c798308e3a
[Server] Escape HTML in webchat (#2368) 
* escape HTML in webchat
* add amp
 2023-07-25 10:27:34 +03:00
Concedo
48c27a9ce1 hotfix for 70b broadcast issues 2023-07-25 01:32:47 +08:00
Александр Герман
9731682ad6
Update Makefile (#345) 
fix requirements for idiotic source file concatenation (lol)
 2023-07-25 00:21:32 +08:00
slaren
41c674161f
make rms_norm_eps a parameter (#2374) 
* make rms_norm_eps a parameter

* add rms_norm_eps to command line

* fix baby llama, test-grad0

* use scientific notation for eps param in the help

ggml-ci
 2023-07-24 17:57:12 +02:00
Concedo
d8d2449bfb better label (+1 squashed commits) 
Squashed commits:

[f573b2c] cuda 3 target arch
 2023-07-24 23:07:31 +08:00
Aarni Koskela
b3f138d058
Chat UI extras (#2366) 
* makefile: correct deps for server

* server: tighten settings layout a little

* server: expose all currently configured generation params in UI

* server: expose remaining generation params, for the adventurous

* server: embetter mirostat fields
 2023-07-24 17:54:22 +03:00
Concedo
7555dae4cc ditch advanced subparsers 2023-07-24 22:40:36 +08:00
Concedo
8a9b40840b Merge branch 'master' into concedo_experimental 
# Conflicts:
#	tests/test-grad0.c
#	tests/test-opt.c
 2023-07-24 20:51:28 +08:00
Concedo
6d71e100fe buff buffers 2023-07-24 20:33:17 +08:00
Georgi Gerganov
5b2b2dc6ae
ggml : sync (unary ops refactor, static-correctness) (#2370) 
* ggml : sync (unary ops, tests)

ggml-ci

* tests : remove unnecessary funcs
 2023-07-24 14:46:21 +03:00
Concedo
825e34baa3 default horde name and better handling for horde (+3 squashed commit) 
Squashed commit:

[fadfa60] better idle handling for horde worker

[a3971e6] updated lite

[2ca2b79] seems to not generate rubbish
 2023-07-24 18:41:41 +08:00
Kawrakow
42f70cb2f6
Fix scalar version of Q5_K when QK_K = 64 (#2362) 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2023-07-24 12:55:02 +03:00
Concedo
c7136f03d9 added support for tensor_split parameter as an advanced parameter. 2023-07-24 17:16:19 +08:00
Concedo
66328fcd80 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	Makefile
 2023-07-24 15:44:26 +08:00
Concedo
94499dba25 added support for 70b llama 2 2023-07-24 15:20:18 +08:00
Concedo
993ba3b026 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	README.md
 2023-07-24 11:59:00 +08:00
Evan Jones
84e09a7d8b
llama : add grammar-based sampling (#1773) 
* llama, main : constrain sampling to grammar

* allow loading grammar from file

* fix whitespace errors

* handle & print parser errors

* add comments to grammar syntax and allow newlines where unambiguous

* add missing include

* support alternates in root rule

* fix bugs with empty token and EOS

* adjust JSON grammar

* remove swp file

* rewrite ternary expressions

Co-authored-by: Henri Vasserman <henv@hot.ee>

* use struct for grammar elements and add Unicode support

* add unicode escapes

* add inverse char ranges

* only sample full tokens (no peeking or truncation)

* llama : minor style changes

blindly applied in online editor - hopefully I didn't break something

* update help text

* add warning message if EOS is disabled

---------

Co-authored-by: Henri Vasserman <henv@hot.ee>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-07-23 23:58:10 -04:00
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