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

554 commits

This branch
This branch
All branches
Author SHA1 Message Date
Georgi Gerganov
e038e01e28
sha : update hashes for 7B and 13B 2023-05-11 21:37:16 +03:00
Georgi Gerganov
5bc286ab18
ggml : fix AVX2 implementation 2023-05-11 21:37:16 +03:00
Georgi Gerganov
bd5e373058
Revert "AVX implementations (#1370)" 
This reverts commit 948d124837.
 2023-05-11 21:37:16 +03:00
Georgi Gerganov
6680244838
ggml : fix Q8_0 and Q8_1 rounding 2023-05-11 21:37:16 +03:00
Georgi Gerganov
582a39fff5
ggml : simplify Q8_1 - no need for low / high sums anymore 2023-05-11 21:37:16 +03:00
Georgi Gerganov
695f3963b1
ggml : preserve old Q4 and Q5 formats 2023-05-11 21:37:16 +03:00
Georgi Gerganov
b7ad385d42
ggml : speed-up Q5_0 + Q5_1 at 4 threads 2023-05-11 21:37:15 +03:00
Georgi Gerganov
09032e0290
llama : fix model magic/version write 2023-05-11 21:37:15 +03:00
Georgi Gerganov
d52172a509
llama : produce error upon loading old model files 2023-05-11 21:37:15 +03:00
Georgi Gerganov
489bd13fad
ggml : uniform 5th bit extraction 2023-05-11 21:37:15 +03:00
Stephan Walter
9e49d20150
AVX implementations (#1370) 2023-05-11 21:37:15 +03:00
Georgi Gerganov
928d2f335f
scripts : add script for measuring the time per token 2023-05-11 21:37:15 +03:00
Georgi Gerganov
83674556b8
ggml : fix Q5_0 quantization 2023-05-11 21:37:15 +03:00
Georgi Gerganov
b08c39b16c
ggml : minor formatting 2023-05-11 21:37:14 +03:00
Georgi Gerganov
4bf1c8a43e
ggml : remove Q4_2 mode 2023-05-11 21:37:14 +03:00
Georgi Gerganov
cdc9607329
ggml : update cuBLAS + normalize variable names 2023-05-11 21:37:14 +03:00
Georgi Gerganov
9472d0ea8b
ggml : fix Q4_1 quantization 2023-05-11 21:37:14 +03:00
Georgi Gerganov
0add6402bd
ggml : remove WASM SIMD bit shuffling + remove vzip for ARM 32-bit 2023-05-11 21:37:14 +03:00
Georgi Gerganov
caaacd5765
ggml : simplify scalar dot 2023-05-11 21:37:14 +03:00
Georgi Gerganov
292a778ca2
ggml : remove Q5_1 bit shuffling (ARM NEON + scalar) 2023-05-11 21:37:13 +03:00
Georgi Gerganov
b37a08f646
ggml : 2x faster scalar implementations 2023-05-11 21:37:13 +03:00
Georgi Gerganov
aa78dfed7d
ggml : remove Q5_0 bit shuffling (ARM NEON) 2023-05-11 21:37:13 +03:00
Georgi Gerganov
9f3285f741
ggml : remove Q4_2 bit shuffling (WIP, BROKEN) 2023-05-11 21:37:13 +03:00
Georgi Gerganov
fd2a137fac
ggml : nibbles_from_floats() + bytes_from_nibbles() (ARM NEON) 2023-05-11 21:37:13 +03:00
Georgi Gerganov
844d2af89d
ggml : remove Q4_1 bit shuffling (ARM NEON + reference) 2023-05-11 21:37:13 +03:00
Georgi Gerganov
5fa47bf6c7
ggml : remove Q4_0 bit shufling (ARM NEON) 2023-05-11 21:37:12 +03:00
CRD716
b608b55a3e
prompts : model agnostic DAN (#1304) 
* add model-agnostic dan prompt

* quick readme update

* save a token

* Revert "quick readme update"

This reverts commit 8dc342c069.
 2023-05-11 18:10:19 +03:00
Evan Jones
cf348a60e0
main : add option to save full output to session (#1338) 
* main : add option to save full output to session

* split behavior into --session and --prompt-cache

* restore original implementation with new names

* PR comments

* move the check for incompatible parameters to gpt_params_parse

* Fix whitespace

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

---------

Co-authored-by: DannyDaemonic <DannyDaemonic@gmail.com>
 2023-05-10 11:37:14 -04:00
DannyDaemonic
e6a46b0ed1
Locale fix for Windows (#1379) 2023-05-09 19:53:28 +02:00
Sami Farin
9f8dbc4787
use pause asm insn in busyloop to run the CPU (13600K) 10 °C cooler (#1314) 
* use pause asm insn in busyloop to run the CPU (13600K) 10 °C cooler

Tested with a 13B model.

* use _mm_pause() in busyloop

* use _mm_pause() in busyloop on x86_64 to reduce power consumption
 2023-05-09 14:29:20 +02:00
DannyDaemonic
41654efea8
Interface improvements and --multiline-input (previously --author-mode) (#1040) 
* Interface improvements
* Multiline input
* Track character width
* Works with all characters and control codes + Windows console fixes
 2023-05-08 19:45:48 -07:00
Georgi Gerganov
56551bc11f
readme : add notice about upcoming breaking change 2023-05-08 22:52:18 +03:00
AlpinDale
fe60904eef
readme : add TOC and Pygmalion instructions (#1359) 2023-05-08 19:33:30 +03:00
Pavol Rusnak
003ba2fb43
llama : fix hparams shadow (#1367) 
fixes #1363
 2023-05-08 17:48:21 +03:00
Georgi Gerganov
f9a6364912
llama : require first token to be BOS (#1303) 
* llama : require first token to be BOS

* scripts : add ppl-run-all.sh

* perplexity : add BOS for each chunk

* readme : update perplexity values after BOS fix

* perplexity : add clarifying comments
 2023-05-08 17:41:54 +03:00
ubik2
95078cc554
convert: add ability to convert safetensors files (#1276) 
* when loading a safetensors file, ignore the metadata header
* check for safetensors files first, and only use PyTorch versions when safetensors aren't available
 2023-05-08 13:54:26 +02:00
Johannes Gäßler
1f48b0abcf
Documented CUDA reproducibility, added warning (#1346) 2023-05-08 02:42:01 +02:00
Henri Vasserman
e1295513a4
CI: add Windows CLBlast and OpenBLAS builds (#1277) 
* Add OpenCL and CLBlast support

* Add OpenBLAS support

* Remove testing from matrix

* change build name to 'clblast'
 2023-05-07 13:20:09 +02:00
swittk
1b0fd45465
ggml : Allow usage of CLBlast alongside Accelerate.framework (#1336) 
Minor edit in ggml.c which originally would prevent OpenCL from loading completely if GGML_USE_ACCELERATE was defined.
Minor speedup in prompt eval time.
 2023-05-06 23:03:23 -04:00
Jed Fox
3924088512
Remove default arguments from sampling functions (#1343) 2023-05-06 17:01:47 -04:00
DaniAndTheWeb
173d0e6419
makefile: automatic Arch Linux detection (#1332) 
This commit is a port of a detection method used in koboldcpp's Makefile in order to automatically set the -lcblas option on Arch Linux
 2023-05-05 23:57:14 +02:00
Erik Scholz
a3b85b28da
ci : add cublas to windows release (#1271) 2023-05-05 22:56:09 +02:00
Pavol Rusnak
921dcee00a
readme: add missing info (#1324) 2023-05-05 16:43:36 +02:00
Ionoclast Laboratories
2d13786e91
Fix for OpenCL / clbast builds on macOS. (#1329) 2023-05-05 14:18:21 +02:00
Benjamin Lecaillon
a90e96b266
Convert.py @staticmethod (#1327) 
* Line 698 has one #staticmethod and should not

otherwise throw error at unpickle.load() as not callable

* Update convert.py

---------

Co-authored-by: Ivan Stepanov <ivanstepanovftw@gmail.com>
 2023-05-05 03:17:07 +03:00
slaren
94c5652fc0
quantize: make output filename optional, default to ggml-model-<ftype>.bin (#1301) 2023-05-05 00:58:56 +02:00
Ivan Stepanov
34d9f22f44
Wrap exceptions in std::exception to verbose output on exception. (#1316) 2023-05-04 18:56:27 +02:00
Ivan Stepanov
d3e8093e9b
convert: support DT_BF16 tensors (#1309) 
Co-authored-by: Pavol Rusnak <pavol@rusnak.io>
 2023-05-04 18:54:37 +02:00
44670
360cfe5bec
readme : add OpenBuddy link (#1321) 2023-05-04 19:33:31 +03:00
44670
2edbdb0f99
main : add --in-suffix option (#1318) 
* adding --in-suffix option

* print input suffix before generation
 2023-05-04 18:41:12 +03:00