Commit Graph

3579 Commits

Author SHA1 Message Date
compilade
c69c63039c
convert_hf : fix Gemma v1 conversion (#8597)
* convert_hf : fix Gemma v1 conversion

* convert_hf : allow renaming tokens, but with a warning

* convert_hf : fix Gemma v1 not setting BOS and EOS tokens
2024-07-20 21:53:01 -04:00
Johannes Gäßler
69c487f4ed
CUDA: MMQ code deduplication + iquant support (#8495)
* CUDA: MMQ code deduplication + iquant support

* 1 less parallel job for CI build
2024-07-20 22:25:26 +02:00
Georgi Gerganov
07283b1a90
gguf : handle null name during init (#8587) 2024-07-20 17:15:42 +03:00
Michael Coppola
940362224d
llama : add support for Tekken pre-tokenizer (#8579)
* llama : Added support for Tekken pre-tokenizer (#8577)

Removed uneeded `vocab.tokenizer_clean_spaces` assignment

* llama : fix order of pre-tokenizers

* * Tekken pre-tokenizer no longer uses clean_up_tokenization_spaces
* Updated chkhsh for Tekken tokenizer

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-07-20 16:43:51 +03:00
Huifeng Ou
69b9945b44
llama.swiftui: fix end of generation bug (#8268)
* fix continuing generating blank lines after getting EOT token or EOS token from LLM

* change variable name to is_done (variable name suggested by ggerganov)

* minor : fix trailing whitespace

* minor : add space

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-07-20 16:09:37 +03:00
Brian
c3776cacab
gguf_dump.py: fix markddown kv array print (#8588)
* gguf_dump.py: fix markddown kv array print

* Update gguf-py/scripts/gguf_dump.py

Co-authored-by: compilade <git@compilade.net>

* gguf_dump.py: refactor kv array string handling

* gguf_dump.py: escape backticks inside of strings

* gguf_dump.py: inline code markdown escape handler added

>>> escape_markdown_inline_code("hello world")
'`hello world`'
>>> escape_markdown_inline_code("hello ` world")
'``hello ` world``'

* gguf_dump.py: handle edge case about backticks on start or end of a string

---------

Co-authored-by: compilade <git@compilade.net>
2024-07-20 17:35:25 +10:00
slaren
87e397d00b
ggml : fix quant dot product with odd number of blocks (#8549)
* ggml : fix iq4_nl dot product with odd number of blocks

* ggml : fix odd blocks for ARM_NEON (#8556)

* ggml : fix iq4_nl dot product with odd number of blocks

* ggml : fix q4_1

* ggml : fix q5_0

* ggml : fix q5_1

* ggml : fix iq4_nl metal

ggml-ci

* ggml : fix q4_0

* ggml : fix q8_0

ggml-ci

* ggml : remove special Q4_0 code for first 2 blocks

* ggml : fix sumf redefinition

---------

Co-authored-by: slaren <slarengh@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-07-19 17:17:27 +02:00
Brian
57b1d4f9eb
convert-*.py: remove add_name from ChatGLMModel class (#8590) 2024-07-20 00:04:38 +10:00
Georgi Gerganov
d197545530
llama : bump max layers from 256 to 512 (#8530)
* llama : bump max layers from 256 to 512

* llama : replace asserts with exceptions
2024-07-19 16:50:47 +03:00
Georgi Gerganov
be0cfb4175
readme : fix server badge 2024-07-19 14:34:55 +03:00
Clint Herron
b57eb9ca4f
ggml : add friendlier error message to fopen errors (#8575)
* Add additional error information when model files fail to load.

* Adding additional error information to most instances of fopen.
2024-07-19 14:05:45 +03:00
Frank Mai
f299aa98ec
fix: typo of chatglm4 chat tmpl (#8586)
Signed-off-by: thxCode <thxcode0824@gmail.com>
2024-07-19 11:44:41 +02:00
Brian
3d0e4367d9
convert-*.py: add general.name kv override (#8571) 2024-07-19 17:51:51 +10:00
Johannes Gäßler
a15ef8f8a0
CUDA: fix partial offloading for ne0 % 256 != 0 (#8572) 2024-07-18 23:48:47 +02:00
65a
705b7ecf60
cmake : install all ggml public headers (#8480)
Co-authored-by: 65a <65a@65a.invalid>
2024-07-18 17:47:12 +03:00
Eric Zhang
0d2c7321e9
server: use relative routes for static files in new UI (#8552)
* server: public: fix api_url on non-index pages

* server: public: use relative routes for static files in new UI
2024-07-18 12:43:49 +02:00
Brian
672a6f1018
convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499)
Main thing is that the default output filename will take this form

{name}{parameters}{finetune}{version}{encoding}{kind}

In addition this add and remove some entries in the KV store and adds a metadata class with automatic heuristics capability to derive some values based on model card content

* No Change:
  - Internal GGUF Spec
    - `general.architecture`
    - `general.quantization_version`
    - `general.alignment`
    - `general.file_type`
  - General Model Details
    - `general.name`
    - `general.author`
    - `general.version`
    - `general.description`
  - Licensing details
    - `general.license`
  - Typically represents the converted GGUF repo (Unless made from scratch)
    - `general.url`
  - Model Source during conversion
    - `general.source.url`

* Removed:
  - Model Source during conversion
    - `general.source.huggingface.repository`

* Added:
  - General Model Details
    - `general.organization`
    - `general.finetune`
    - `general.basename`
    - `general.quantized_by`
    - `general.size_label`
  - Licensing details
    - `general.license.name`
    - `general.license.link`
  - Typically represents the converted GGUF repo (Unless made from scratch)
    - `general.doi`
    - `general.uuid`
    - `general.repo_url`
  - Model Source during conversion
    - `general.source.doi`
    - `general.source.uuid`
    - `general.source.repo_url`
  - Base Model Source
    - `general.base_model.count`
    - `general.base_model.{id}.name`
    - `general.base_model.{id}.author`
    - `general.base_model.{id}.version`
    - `general.base_model.{id}.organization`
    - `general.base_model.{id}.url` (Model Website/Paper)
    - `general.base_model.{id}.doi`
    - `general.base_model.{id}.uuid`
    - `general.base_model.{id}.repo_url` (Model Source Repository (git/svn/etc...))
  - Array based KV stores
    - `general.tags`
    - `general.languages`
    - `general.datasets`

---------

Co-authored-by: compilade <git@compilade.net>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
2024-07-18 20:40:15 +10:00
RunningLeon
3807c3de04
server : respect --special cli arg (#8553) 2024-07-18 11:06:22 +03:00
Johannes Gäßler
e02b597be3
lookup: fibonacci hashing, fix crashes (#8548) 2024-07-17 23:35:44 +02:00
Al Mochkin
b3283448ce
build : Fix docker build warnings (#8535) (#8537) 2024-07-17 20:21:55 +02:00
Brian
30f80ca0bc
CONTRIBUTING.md : remove mention of noci (#8541) 2024-07-17 17:57:06 +03:00
hipudding
1bdd8ae19f
[CANN] Add Ascend NPU backend (#6035)
* [CANN] Add Ascend NPU backend

Ascend is a full-stack AI computing infrastructure for industry
applications and services based on Huawei Ascend processors and
software.

CANN (Compute Architecture of Neural Networks), developped by
Huawei, is a heterogeneous computing architecture for AI.

Co-authored-by: wangshuai09 <391746016@qq.com>

* delete trailing whitespaces

* Modify the code based on review comment

* Rename LLAMA_CANN to GGML_CANN

* Make ggml-common.h private

* add ggml_cann prefix for acl funcs

* Add logging for CANN backend

* Delete Trailing whitespace

---------

Co-authored-by: wangshuai09 <391746016@qq.com>
2024-07-17 14:23:50 +03:00
Masaya, Kato
da3913d8f9
batched: fix n_predict parameter (#8527) 2024-07-17 10:34:28 +03:00
Georgi Gerganov
d65a8361fe
llama : disable context-shift for DeepSeek v2 (#8501) 2024-07-17 10:32:59 +03:00
Johannes Gäßler
5e116e8dd5
make/cmake: add missing force MMQ/cuBLAS for HIP (#8515) 2024-07-16 21:20:59 +02:00
Brian
1666f92dcd
gguf-hash : update clib.json to point to original xxhash repo (#8491)
* Update clib.json to point to Cyan4973 original xxhash

Convinced Cyan4973 to add clib.json directly to his repo, so can now point the clib package directly to him now. Previously pointed to my fork with the clib.json package metadata

https://github.com/Cyan4973/xxHash/pull/954

* gguf-hash: readme update to point to Cyan4973 xxHash repo [no ci]
2024-07-16 10:14:16 +03:00
Steve Bonds
37b12f92ab
export-lora : handle help argument (#8497)
The --help option on export-lora isn't accepted as valid. The help still gets displayed by default, but the script exits with an error message and nonzero status.
2024-07-16 10:04:45 +03:00
Georgi Gerganov
0efec57787
llama : valign + remove unused ftype (#8502) 2024-07-16 10:00:30 +03:00
compilade
7acfd4e8d5
convert_hf : faster lazy safetensors (#8482)
* convert_hf : faster lazy safetensors

This makes '--dry-run' much, much faster.

* convert_hf : fix memory leak in lazy MoE conversion

The '_lazy' queue was sometimes self-referential,
which caused reference cycles of objects old enough
to avoid garbage collection until potential memory exhaustion.
2024-07-15 23:13:10 -04:00
Xuan Son Nguyen
97bdd26eee
Refactor lora adapter support (#8332)
* lora: load to devide buft

* add patch tensor function

* correct tensor patch

* llama_lora_adapter_apply

* correct ggml_backend_tensor_copy

* add llm_build_mm

* fix auto merge

* update based on review comments

* add convert script

* no more transpose A

* add f16 convert

* add metadata check

* add sanity check

* fix ftype

* add requirements

* fix requirements

* fix outfile

* conversion: only allow selected models

* fix types

* cuda : do not use dmmv if the tensor does not have enough cols

* llama : lora fixes

* do not disable mmap with lora

Co-authored-by: slaren <slarengh@gmail.com>

* llm_build_lora_mm_id

* convert_lora : MoE LoRA conversion support

* convert_lora : prefer safetensors, similarly to convert_hf

* convert_hf : simplify modify_tensors for InternLM2

* convert_lora : lazy conversion

* llama : load and use alpha from LoRA adapters

* llama : use llm_build_lora_mm in most model graphs

* auto scale

* Revert "auto scale"

This reverts commit 42415a4874.

* remove redundant params

* Apply suggestions from code review

Co-authored-by: slaren <slarengh@gmail.com>

* change kv metadata

* move add_type to __init__

* convert_hf : move add_type to main()

* convert_lora : use the GGUFWriter from Model instead of overwriting it

---------

Co-authored-by: slaren <slarengh@gmail.com>
Co-authored-by: Francis Couture-Harpin <git@compilade.net>
2024-07-15 20:50:47 +02:00
Xuan Son Nguyen
4db8f60fe7
fix ci (#8494) 2024-07-15 19:23:10 +02:00
Daniel Bevenius
8fac431b06
ggml : suppress unknown pragma 'GCC' on windows (#8460)
This commit adds a macro guard to pragma GCC to avoid the following
warning on windows:

```console
C:\llama.cpp\ggml\src\ggml-aarch64.c(17,9): warning C4068:
unknown pragma 'GCC' [C:\lama.cpp\build\ggml\src\ggml.vcxproj]
```
2024-07-15 15:48:17 +03:00
M-A
f17f39ff9c
server: update README.md with llama-server --help output [no ci] (#8472)
The README.md had a stale information. In particular, the --ctx-size
"defaults to 512" confused me and I had to check the code to confirm
this was false. This the server is evolving rapidly, it's probably
better to keep the source of truth at a single place (in the source) and
generate the README.md based on that.

Did:

    make llama-server
    ./llama-server --help > t.txt
    vimdiff t.txt examples/server/README.md

I copied the content inside a backquote block. I would have preferred
proper text but it would require a fair amount of surgery to make the
current output compatible with markdown. A follow up could be to
automate this process with a script.

No functional change.
2024-07-15 15:04:56 +03:00
Georgi Gerganov
9104bc20ed
common : add --no-cont-batching arg (#6358) 2024-07-15 14:54:58 +03:00
NikolaiLyssogor
fc690b018e
docs: fix links in development docs [no ci] (#8481)
Fixes a few links to within the repo that were broken in the reorganization of the
documentation in #8325.
2024-07-15 14:46:39 +03:00
Meng, Hengyu
16bdfa42ac
[SYCL] add concat through dim 1/2 (#8483)
* add concat through dim 1/2
2024-07-15 19:32:15 +08:00
Georgi Gerganov
3dfda05956
llama : de-duplicate deepseek2 norm 2024-07-15 14:10:39 +03:00
0cc4m
bda62d7999
Vulkan MMQ Fix (#8479)
* Fix incoherence by adding missing LOAD_VEC_A parameter

* Fix Vulkan op result checker build error
2024-07-15 09:38:52 +02:00
compilade
090fca7a07
pydantic : replace uses of __annotations__ with get_type_hints (#8474)
* pydantic : replace uses of __annotations__ with get_type_hints

* pydantic : fix Python 3.9 and 3.10 support
2024-07-14 19:51:21 -04:00
Georgi Gerganov
aaab2419ea
flake.lock: Update (#8475)
Flake lock file updates:

• Updated input 'nixpkgs':
    'github:NixOS/nixpkgs/9f4128e00b0ae8ec65918efeba59db998750ead6?narHash=sha256-rwz8NJZV%2B387rnWpTYcXaRNvzUSnnF9aHONoJIYmiUQ%3D' (2024-07-03)
  → 'github:NixOS/nixpkgs/7e7c39ea35c5cdd002cd4588b03a3fb9ece6fad9?narHash=sha256-EYekUHJE2gxeo2pM/zM9Wlqw1Uw2XTJXOSAO79ksc4Y%3D' (2024-07-12)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-14 08:54:02 -07:00
Georgi Gerganov
73cf442e7b
llama : fix Gemma-2 Query scaling factors (#8473)
* 9B - query_pre_attn_scalar = 256 not 224

See 03e657582d

Gemma 9b should use 256 and not 224 (self.config.hidden_size // self.config.num_attention_heads)

* llama : fix Gemma-2 Query scaling factor

ggml-ci

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>
2024-07-14 14:05:09 +03:00
Brian
e236528e76
gguf_hash.py: Add sha256 (#8470)
* gguf_hash.py: Add sha256

* gguf_hash.py: rename string UUIDv5 --> uuid

* Apply suggestions from code review

Co-authored-by: compilade <git@compilade.net>

---------

Co-authored-by: compilade <git@compilade.net>
2024-07-14 16:47:14 +10:00
compilade
fa79495bb4
llama : fix pre-tokenization of non-special added tokens (#8228)
* llama : fix mpt and olmo pre-tokenizer

* llama : pre-tokenize non-special user-defined tokens first

* llama : fix detection of control-like user-defined tokens

* convert_hf : identify which user-defined tokens are control tokens

Only used in _set_vocab_gpt2() for now.

* convert_hf : identify more added control tokens for SPM tokenziers

This makes Gemma and Gemma-2 tokenize pretty much EVERYTHING correctly,
including HTML tags and consecutive spaces,
but it unfortunately requires model re-conversion.

There seems to be a weird behavior of the HF tokenizer for Gemma,
which prefers to use the 16-space token over more lengthy space tokens,
while using the SentencePiece tokenizer does not do this.
(the implementation in llama.cpp has the same behavior as SentencePiece)

* llama : fix wrong pre-tokenization of byte tokens

* llama : fix Viking pre-tokenizer regex

The order was previously wrong, which caused errors in some tests.

* llama : fix command-r detokenization

* convert_hf : reduce usages of the UNKNOWN token type

* llama : add UNKNOWN tokens in the special tokens cache

* convert_hf : reduce usages of UNKNOWN for InternLM2

This makes the changes from #8321 more consistent
with the other changes made here.

* test-tokenizer-random : reduce potential confilcts with #8379

* test-tokenizer-random : add a failing edge case for falcon
2024-07-13 23:35:10 -04:00
bandoti
17eb6aa8a9
vulkan : cmake integration (#8119)
* Add Vulkan to CMake pkg

* Add Sycl to CMake pkg

* Add OpenMP to CMake pkg

* Split generated shader file into separate translation unit

* Add CMake target for Vulkan shaders

* Update README.md

* Add make target for Vulkan shaders

* Use pkg-config to locate vulkan library

* Add vulkan SDK dep to ubuntu-22-cmake-vulkan workflow

* Clean up tabs

* Move sudo to apt-key invocation

* Forward GGML_EXTRA_LIBS to CMake config pkg

* Update vulkan obj file paths

* Add shaderc to nix pkg

* Add python3 to Vulkan nix build

* Link against ggml in cmake pkg

* Remove Python dependency from Vulkan build

* code review changes

* Remove trailing newline

* Add cflags from pkg-config to fix w64devkit build

* Update README.md

* Remove trailing whitespace

* Update README.md

* Remove trailing whitespace

* Fix doc heading

* Make glslc required Vulkan component

* remove clblast from nix pkg
2024-07-13 18:12:39 +02:00
Georgi Gerganov
c917b67f06
metal : template-ify some of the kernels (#8447)
ggml-ci
2024-07-13 18:32:33 +03:00
Georgi Gerganov
4e24cffd8c
server : handle content array in chat API (#8449)
* server : handle content array in chat API

* Update examples/server/utils.hpp

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

---------

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
2024-07-12 14:48:15 +03:00
Georgi Gerganov
6af51c0d96
main : print error on empty input (#8456) 2024-07-12 14:48:04 +03:00
Daniel Bevenius
f53226245f
llama : suppress unary minus operator warning (#8448)
This commit updates the _try_copy lambda and moves the unary minus
operator to after the cast to int32_t.

The motivation for this that currently the following warning is
generated on windows:

```console
llama.cpp\src\llama.cpp(21147,30): warning C4146: unary minus operator
applied to unsigned type, result still unsigned
```
2024-07-12 12:05:21 +03:00
Douglas Hanley
c3ebcfa148
server : ensure batches are either all embed or all completion (#8420)
* make sure batches are all embed or all non-embed

* non-embedding batch for sampled tokens; fix unused params warning
2024-07-12 11:14:12 +03:00
Armen Kaleshian
8a4441ea1a
docker : fix filename for convert-hf-to-gguf.py in tools.sh (#8441)
Commit b0a4699 changed the name of this script from convert-hf-to-gguf.py to
convert_hf_to_gguf.py breaking how convert is called from within a Docker
container.
2024-07-12 11:08:19 +03:00