Commit Graph

4004 Commits

Author SHA1 Message Date
grahameth
be475f60af
llama.cpp : fix wrong vsnprintf call in MS compiler (#2856)
Co-authored-by: grahameth <->
2023-08-28 18:38:12 +03:00
Ronny Brendel
3af6b86301
ggml : tiny ggml_vec_dot_q4_K_q8_K AVX2 improvement (#2819) 2023-08-28 15:51:08 +03:00
Georgi Gerganov
35feac6560
ggml : sync (mem align to header + conv_transpose_2d fixes + ggml_alloc) (#2852)
* ggml : sync (mem align to header + conv_transpose_2d fixes)

ggml-ci

* ggml-alloc : minor fix

* ggml-alloc : sync more fixes
2023-08-28 14:24:53 +03:00
Johannes Gäßler
92b1bbd2ec
CUDA: fix RoPE asserts, block sizes (#2833) 2023-08-28 14:23:55 +03:00
igarnier
dd0dc366da
llama.h : add missing struct keyword for C compat in callback type (#2847) 2023-08-28 11:19:59 +03:00
Georgi Gerganov
f55538c3cc
metal : fix memory leak (#2762)
* metal : fix memory leak

* metal : fix encoders memory leak

* metal : clean up more memory resources

* metal : fix more leaks

* metal : reuse dispatch queue + autoreleasepool

* metal : reuse array for command buffers and encoders

* ggml : assert for odd number of blocks on ARM

15M tinyllama is an example
2023-08-28 10:59:08 +03:00
Cebtenzzre
ebcee207b6
quantize : make output filename optional again (#2823)
* quantize : make output filename optional again

* quantize : fix path parsing on Windows

suggested by @slaren
2023-08-28 09:32:25 +03:00
JohnnyB
3e8ff47af6
devops : added systemd units and set versioning to use date. (#2835)
* Corrections and systemd units

* Missing dependency clblast
2023-08-28 09:31:24 +03:00
Georgi Gerganov
103cfafc77
gguf : fix strings to not be null-terminated (#2839)
* gguf : fix strings to not be null-terminated

ggml-ci

* gguf : fix gguf_add_tensor name
2023-08-27 21:50:22 +03:00
Georgi Gerganov
c10704d01e
llama : fix MPI threads (close #2827) 2023-08-27 18:55:41 +03:00
Olivier Chafik
230d46c723
examples : update llama2.c converter to read vocab and write models in GGUF format (#2751)
* llama2.c: direct gguf output (WIP)

* Simplify vector building logic

* llama2.c gguf conversion: fix token types in converter

* llama2.c: support copying vocab from a llama gguf model file

* llama2.c: update default path for vocab model + readme

* llama2.c: use defines for gguf keys

* llama2.c: escape whitespaces w/ U+2581 in vocab converter the llama.cpp way

* llama2.c converter: cleanups + take n_ff from config
2023-08-27 17:13:31 +03:00
Kawrakow
463173a6c0
llama : speedup tokenization (#2831)
* Speedup tokenization

On current master it takes ~3.2 seconds to tokenize
Wikitext. With this change it becomes ~525 ms.

* Fixit: it was missing the piece after the last found occurence

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-08-27 16:50:33 +03:00
Georgi Gerganov
eaa13a48ff
falcon : fix CUDA inference by making K and Q contiguous (#2830)
* falcon : fix CUDA inference by making K and Q contiguous

ggml-ci

* cuda : add assert to guard from non-cont ropes
2023-08-27 16:40:48 +03:00
Georgi Gerganov
da7455d046
readme : fix headings 2023-08-27 15:52:34 +03:00
Georgi Gerganov
25423e9185
scripts : helper convert script 2023-08-27 15:24:58 +03:00
Kawrakow
a6d1189fdd
k_quants tuning for Falcon-7b (#2816)
* Make ggml-cuda.cu build with QK_K = 64

Using LLAMA_CUDA_FORCE_DMMV = ON and -nommq it runs and produces
a meaningful result.

* k_quants tuning for Falcon-7b

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-08-27 15:19:59 +03:00
Georgi Gerganov
c48c5bb0b0
readme : update hot topics 2023-08-27 14:44:35 +03:00
Georgi Gerganov
d0cee0d36d
gguf : add 64-bit support (GGUF v2) (#2821)
* gguf : bump version to 2

* gguf : add support for 64-bit (no backwards comp yet)

* gguf : v1 backwards comp

* gguf.py : bump GGUF version

* gguf.py : uint64_t on all lengths, sizes and counts, enums still uint32_t

* gguf.py : string lengths uint32_t

* gguf : update all counts to 64-bit

* gguf.py : string len uint64_t and n_dims uint32_t

* gguf : fix typo

* llama.cpp : print gguf version

---------

Co-authored-by: klosax <131523366+klosax@users.noreply.github.com>
2023-08-27 14:19:54 +03:00
Georgi Gerganov
edd4c14817
llama : more tokenizer fixes (#2810)
* tests : write a Python tokenizer test (wip)

* llama : prefix input text for tokenization with whitespace

* llama : distinguish pieces from decoded text + fix detokenization

* common : add comments

* examples : no longer manually add leading space when tokenizing

* tests : use Python to generate tokenizer tests for C++

* tests : add option to tokenize text files

ggml-ci

* tests : add test-tokenizer-1.py

* llama.cpp : fix LF token

* hellaswag : move the concat space for clarity

* tests : add falcon tests (py + cpp, currently do not pass Unicode)

ggml-ci

* common : temporary separate llama_detokenize calls for SPM and BPE

---------

Co-authored-by: klosax <131523366+klosax@users.noreply.github.com>
2023-08-27 14:19:19 +03:00
Przemysław Pawełczyk
1591e2e590
ggml : detect SSSE3 (#2825)
* ggml : add ggml_cpu_has_ssse3

* llama : show SSSE3 in system info
2023-08-27 11:10:25 +03:00
slaren
789c8c945a
ci : add LoRA test to CI (#2650)
* ci : add lora test

ggml-ci

* move lora summary to the top, add lora logs

ggml-ci

* ci : decrease CPU ppl runs to 2 to avoide 20 min timeout

ggml-ci

* add 7b lora test

use 1 thread for CUDA generation tests

ggml-ci

* add test with q8_0 (cpu only)

ggml-ci

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-08-27 10:03:27 +03:00
Bruce MacDonald
c1ac54b77a
server : add /detokenize endpoint (#2802)
* Add a /detokenize endpoint to the example server

* remove trailing white-space
2023-08-27 07:11:45 +08:00
Kerfuffle
730d9c681e
convert.py : advanced option (#2753)
* Allow convert.py to convert to q8_0

Fix issue with bounded_parallel_map and greedy consuming iterator

Display elapsed time during conversion

* Add --concurrency option

Minor improvements to help text

Clean up bounded_parallel_map function a bit

* Massive speed improvement thanks to Cebtenzzre

* Refactor types
2023-08-26 23:13:36 +03:00
Tim Miller
c7d92e6dfe
llama : use Unicode Escape Sequence to replace encoded characters (#2814)
The use of special characters within source files can break compiling on some computers with different region and language settings. Using Unicode escape sequences should allow for the code to be compiled on all setups without needing to change your computers settings or switch regions.
2023-08-26 21:27:07 +03:00
Tungsten842
61d1a2895e
flake.nix : add rocm support and cleanup (#2808) 2023-08-26 21:19:44 +03:00
Cebtenzzre
741ca7dd1c
llama : move #includes out of _GNU_SOURCE conditional (#2817) 2023-08-26 21:17:51 +03:00
Dr. Tom Murphy VII Ph.D
72f895c923
main : fix bug (penalize_nl=false doesn't work) + suppress warning on mingw (#1528)
* Fix bug in main.cpp where penalize_nl=false has no effect. It modifies the underlying logits array, but at this point we are already working on the candidates copy.

* Suppress redefinition warning for NOMINMAX on mingw. In my installation, this macro is already defined by /usr/lib/gcc/x86_64-w64-mingw32/11/include/c++/x86_64-w64-mingw32/bits/os_defines.h:45.

* main : fix indentation

* main : pass ctx to llama_token_nl()

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-08-26 21:12:56 +03:00
Cebtenzzre
50526f37eb
llama : use std::abs in llama_sample_tail_free (#2800)
Plain 'abs' casts the input to int.
2023-08-26 19:53:52 +03:00
Georgi Gerganov
04f4b1eb10
k-quants : remove unnecessary tensor shape restrictions (#2811) 2023-08-26 17:37:35 +03:00
Kawrakow
7592375403
Better perplexity for 2- and 3-bit quantization for LLaMA-v2-70B (#2807)
* Better perplexity for 2- and 3-bit quantization for the 70B model

* PR comment

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-08-26 17:27:49 +03:00
Kawrakow
771551a793
Fix HellaSwag (#2805)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-08-26 16:48:53 +03:00
Volodymyr Vitvitskyi
f305bad11e
flake : build llama.cpp on Intel with nix (#2795)
Problem
-------
`nix build` fails with missing `Accelerate.h`.

Changes
-------
- Fix build of the llama.cpp with nix for Intel: add the same SDK frameworks as
for ARM
- Add `quantize` app to the output of nix flake
- Extend nix devShell with llama-python so we can use convertScript

Testing
-------
Testing the steps with nix:
1. `nix build`
Get the model and then
2. `nix develop` and then `python convert.py models/llama-2-7b.ggmlv3.q4_0.bin`
3. `nix run llama.cpp#quantize -- open_llama_7b/ggml-model-f16.gguf ./models/ggml-model-q4_0.bin 2`
4. `nix run llama.cpp#llama -- -m models/ggml-model-q4_0.bin -p "What is nix?" -n 400 --temp 0.8 -e -t 8`

Co-authored-by: Volodymyr Vitvitskyi <volodymyrvitvitskyi@SamsungPro.local>
2023-08-26 16:25:39 +03:00
Nigel Bosch
a2ca4e9de9
Handle null rope scaling value (#2793) 2023-08-26 14:11:17 +02:00
klosax
2ba83c8685
Fix spm whitespaces (#2806)
* llama.cpp : fix spm whitespace escaping + clean up

* main.cpp : spm - add whitespace in front of prompt

* test-tokenizer-0.cpp : spm - add whitespace in front of prompt
2023-08-26 13:45:53 +02:00
lon
bae5c5f679
examples : skip unnecessary external lib in server README.md how-to (#2804) 2023-08-26 16:07:43 +08:00
Marcus Dunn
232caf3c15
llama : fix struct decl (#2790) 2023-08-25 19:17:15 +03:00
Kawrakow
d046dcee08
Faster perplexity computation (#2786)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-08-25 19:05:02 +03:00
Matt Pulver
c82742ac9c
llama : add llama_beam_search() (#2267)
* Add llama_beam_search().

* Add '// Beam search' heading to llama.{h,cpp} after llama_grammar_accept_token().

* Add space around * pointers and & references.

* Add spaces around comparison and assignment operators.

* Prefer west const.

* Use llama_ prefix for structs in global namespace.

* Delete obsolete comment from an earlier revision.

* Change eos to eob in llama_beam and llama_beam_view structs.
2023-08-25 18:18:48 +03:00
Nigel Bosch
28b2c996ca
convert.py : Get rope scale from HuggingFace models (#2772)
* Get rope scale from HF models

* Save rope scale only for linear scaling

* Rewrite for clarity
2023-08-25 16:41:52 +02:00
slaren
154725c543
llama-bench : add model sizes (#2771)
* llama-bench : add model sizes

* more compact markdown output

* back to GiB

* adjust column sizes
2023-08-25 15:16:19 +02:00
slaren
12e2e33a97
convert.py : export rope freq_base when converting CodeLlama from an HF model (#2773) 2023-08-25 14:08:53 +02:00
Jhen-Jie Hong
29674ab4e8
server : display token probabilities in the UI (#2489)
* server : add n_probs param in chat UI

* server : keep message data array & show in probabilites component

* server : add simple popover component

* server : fix completion_probabilities undefined if not set n_probs

* server : implement Probabilites

* server : handle bytes

* server : make n_probs max to 10 for easy scroll

* server : adjust for dark/light mode

* server : Fix regenerated prompt

* server : update index.html.hpp

* server : convert prob to percentage + show original value as div title

* server : fix Probabilites not used if included empty str

* server : skip byte pair in display probabilites

* server : remove array check of completion_probabilities in messages

* skip empty array or byte pair (> 1) in Probabilites

* generate index.html.hpp

* fix incorrect prob convert if the str is already a known token

* use final response to show probabilities on stop

* revert unnecessary change

* correct probabilites usage

* remove unused function

* always send partial response for get correct probs of last to_send

* fix typo

* fix content of format_final_response

* refactor probs render & make pColor transparent if not found

* send empty string when got stop_pos in partial

* avoid unnecessary empty data event & send rest of partial tokens on stop

* use <br /> for new line

* skip -1 tok in loop to avoid send '' on end

* trim last new lines on stop

* revert unnecessary change
2023-08-25 18:32:45 +08:00
Georgi Gerganov
5439a0ab57
ci : pip install gguf in editable mode (#2782)
ggml-ci
2023-08-25 13:03:25 +03:00
M. Yusuf Sarıgöz
8194cd8772
gguf : export objects to user code (#2780)
* gguf export more objects to user code

* gguf export all objects to user code for now

* gguf : bump version
2023-08-25 12:43:41 +03:00
Henri Vasserman
6bbc598a63
ROCm Port (#1087)
* use hipblas based on cublas
* Update Makefile for the Cuda kernels
* Expand arch list and make it overrideable
* Fix multi GPU on multiple amd architectures with rocblas_initialize() (#5)
* add hipBLAS to README
* new build arg LLAMA_CUDA_MMQ_Y
* fix half2 decomposition
* Add intrinsics polyfills for AMD
* AMD assembly optimized __dp4a
* Allow overriding CC_TURING
* use "ROCm" instead of "CUDA"
* ignore all build dirs
* Add Dockerfiles
* fix llama-bench
* fix -nommq help for non CUDA/HIP

---------

Co-authored-by: YellowRoseCx <80486540+YellowRoseCx@users.noreply.github.com>
Co-authored-by: ardfork <134447697+ardfork@users.noreply.github.com>
Co-authored-by: funnbot <22226942+funnbot@users.noreply.github.com>
Co-authored-by: Engininja2 <139037756+Engininja2@users.noreply.github.com>
Co-authored-by: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com>
Co-authored-by: jammm <2500920+jammm@users.noreply.github.com>
Co-authored-by: jdecourval <7315817+jdecourval@users.noreply.github.com>
2023-08-25 12:09:42 +03:00
Georgi Gerganov
3f460a2b72
cuda : add RoPE kernel for mode == 2 (NeoX) (#2760)
* cuda : add RoPE kernel for mode == 2 (NeoX)

* falcon : do not offload the embeddings layer
2023-08-25 11:55:59 +03:00
M. Yusuf Sarıgöz
87e3733f24
gguf : make gguf pip-installable
* gitignore : add dist and rm pyproject.toml

* gguf: prepare as Pip package

* gguf: prepare as Pip package

* gguf : fix line endings

* requirements : add gguf

* gguf : update readme with build notes

* gguf : update readme with build notes

* gguf : add notes for tests
2023-08-25 09:26:05 +03:00
Shouzheng Liu
b91ad7f461
ggml-alloc : enlarge size of parse_seq (#2776)
Since we also store barriers in this array, we need to double its size.
2023-08-25 08:58:00 +03:00
Marcus Dunn
2e5f70a25f
Added enum to llama_token_get_type return type (#2774) 2023-08-24 23:49:30 +02:00
slaren
d0f77b1353
convert.py : try to determine n_ctx automatically for CodeLlama (#2770) 2023-08-24 21:10:39 +02:00