This enforces a check that -fno-finite-math-only was set and that the operating
compiling mode is not in finite maths mode. This is because during rewriting of
silu and softmax for cpu ggerganov#7154 there emerged an issue where the result that was
observed when >1 slot was nondeterministic as found by @JohannesGaessler.

@LostRuins narrowed the problem down to -ffinite-math-only which was theorised
to be due to SiLU, instead of flushing small values to 0, returns NaN or some 
other garbage. @jart proposed a fix that @ggerganov then implemented in this fix

ref ggerganov#7154 (comment)

* Add per token attributes enum
* Using phi-3 for testing 'rstrip'
* Using jina-v2 for testing 'lstrip'
* Brute force test for 'lstrip' and 'rstrip'
* Implement 'rstrip' and 'lstrip'
* Update phi-3 GGUF file (obsolete since 917dc8c)
* Replace llama_token_type with llama_token_attribs

This adds tags and android ndk into the git ignore list

* Improve hipBLAS support in CMake

This improves the detection of the correct CMAKE_PREFIX_PATH when using different distributions or a self-built ROCm SDK.

* Set ROCM_PATH correctly

…erganov#7722)

compare-commits.sh : hide stdout, use -oe to print markdown

ggml-ci

* common : gpt_params_parse do not print usage

* common : rework usage print (wip)

* common : valign

* common : rework print_usage

* infill : remove cfg support

* common : reorder args

* server : deduplicate parameters

ggml-ci

* common : add missing header

ggml-ci

* common : remote --random-prompt usages

ggml-ci

* examples : migrate to gpt_params

ggml-ci

* batched-bench : migrate to gpt_params

* retrieval : migrate to gpt_params

* common : change defaults for escape and n_ctx

* common : remove chatml and instruct params

ggml-ci

* common : passkey use gpt_params

Previously the code would have failed to cope in the case that the
number of nodes changes in an existing CUDA graph. This fixes the
issue by removing an unnecessary conditional.

-ins and --instruct were moved in ggerganov#7675

I have adjusted the README accordingly.
There was no trace of --chatml in the README.

* ggml : unify rope norm/neox (CPU)

* ggml : fix compile warning

* ggml : remove GLM rope mode

ggml-ci

* metal : better rope implementation

ggml-ci

* cuda : better rope implementation

ggml-ci

* naming : n_orig_ctx -> n_ctx_orig

ggml-ci

* dev : add reminders to update backends

ggml-ci

* vulkan : fix ggml_rope_ext() usage

* cuda : fix array size + indents

ggml-ci

* CUDA: refactor mmq, dmmv, mmvq

* fix out-of-bounds write

* struct for qk, qr, qi

* fix cmake build

* mmq_type_traits

* add openmp lib to dockerfiles

* build only main and server in their docker images

* feat: add changes to handle jina v2 base code

* fix: do not complicate things

* fix: fix the usage of the code model

* fix: fix comments

* fix: fix linting issues

* fix: remove ollama patches

* style : minor

---------

Co-authored-by: Georgi Gerganov <[email protected]>

* grammars: x{min,max} repetition operator + tweak +/*/? to avoid duplication of original over alternates

* grammars: handle `x{n}` and fix `x{n,n}`

* grammars: document new repetition operators

* grammars: uniform use of int for min & max

* grammars: refactor parser test

* grammar: parsing tests w/ natural pretty print of updated expectations

* grammars: much prettier print of expectations (+ TEST_GRAMMAR_PARSER_PRINT_ALL=1 to force all)

* grammars: improve test pretty print again

* grammars: pretty print rules and chars

* grammars: fix copy rule skipping

* grammars: disallow `a{,}` (not allowed in regexps)

* Update common/grammar-parser.cpp

Co-authored-by: Clint Herron <[email protected]>

* grammars: fix copy rule skipping (again) & display of expectations

* grammars: more test cases

* grammars: update reps parsing to bring ? / * / + closer to before

* json: use new GBNF repetitions{m,n} syntax

* grammars: update performance gotchas w/ repetition advice

* Update examples/json_schema_to_grammar.py

Co-authored-by: Clint Herron <[email protected]>

* Update examples/server/public/json-schema-to-grammar.mjs

Co-authored-by: Clint Herron <[email protected]>

* grammars: comment on rule repetitions

* grammars: ensure unambiguous number alternatives

* grammar: nit typo switched error msgs

* grammar: nit numbering in comment

* json: update numeric rule to be unambiguous

* Apply suggestions from code review

Co-authored-by: Clint Herron <[email protected]>

* Update examples/server/public/json-schema-to-grammar.mjs

Co-authored-by: Clint Herron <[email protected]>

* json: fix integral-part

* grammar: add repetition tests

---------

Co-authored-by: Clint Herron <[email protected]>

derievatives --> derivatives

…ov#6467)

* Added support for . (any characer) token in grammar engine.

* Add integration tests for any-character symbol.

* imatrix : migrate to gpt_params

ggml-ci

* imatrix : add --save-frequency cli arg

* common : fix --no-ppl

* imatrix : detect nan/inf values

* quantize : check imatrix for nan/inf values

* avoid to get prompt in infill mode and embedding mode

* remove embedding mode

* refactor format

---------

Co-authored-by: wudexiang <[email protected]>

common depends on pthreads in Linux

* vulkan : reuse parent extra for views

* Fix validation error when multiple compute contexts are used in a graph

---------

Co-authored-by: 0cc4m <[email protected]>

…7728)

* server : Smart selection of available slot using Longest Common Substring

* add usage

* remove trailing whitespaces

* Use Longest Common Prefix (LCP) instead of LCS

* Rename argument

* url: save -mu download to new cache location

* url: fs_get_cache_file_path util

* url: tweak sig of fs_get_cache_file

…ov#7682)" (ggerganov#7808)

This reverts commit 9422c5e.

…nov#7827)

Main changes of this PR is to consolidate GGUFWriter.add_key and GGUFWriter.add_val into GGUFWriter.add_key_value. 

In addition use_temp_file is now opt-in instead of opt-out defaulting to False.

Also GGUFWriter now does not require output file name until when actually writing to it.

And GGUFWriter doesn't really need to eagerly prepare the data layout of the metadata

In ggerganov#7075, to fix the conversion of (some) models using model-00001-of-00001.safetensors instead of model.safetensors for a single model part we simply used the same logic as the part count to get the part names. 

But this doesn't always work correctly, like when unusual additional model files like consolidated.safetensors in https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3 are present.

This commit matching both the prefix and the suffix of the model part names should fix this problem without breaking any previously-supported upstream models. But according to report by @teleprint-me there is still some
persistent problem, but shall do in the meantime.

…ov#7693)

 `--model-name` argument was added a while ago but did not do anything.
This commit fixes this issue and enables this feature.

…gerganov#7830)

…and squash merges [no ci] (ggerganov#7700)

This commit adds pull_request_template.md and CONTRIBUTING.md . It focuses on explaining to contributors the need to rate PR complexity level, when to add [no ci] and how to format PR title and descriptions.

Co-authored-by: Brian <[email protected]>
Co-authored-by: compilade <[email protected]>

Flake lock file updates:

• Updated input 'nixpkgs':
    'github:NixOS/nixpkgs/ad57eef4ef0659193044870c731987a6df5cf56b?narHash=sha256-SzDKxseEcHR5KzPXLwsemyTR/kaM9whxeiJohbL04rs%3D' (2024-05-29)
  → 'github:NixOS/nixpkgs/051f920625ab5aabe37c920346e3e69d7d34400e?narHash=sha256-4q0s6m0GUcN7q%2BY2DqD27iLvbcd1G50T2lv08kKxkSI%3D' (2024-06-07)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

Signed-off-by: Ben Ashbaugh <[email protected]>

* CUDA: int8 tensor cores for MMQ (legacy quants)

* fix out-of-bounds writes

* __builtin_assume -> GGML_CUDA_ASSUME

* fix writeback returning too early

…ar examples & converters (ggerganov#7841)

* json: fix char pattern in grammar converters

* json: prevent number precision & whitespace runaways in example grammars

* json: add doc to grammar readme

…etty print (ggerganov#7866)

* try to fix CUDA ci with --allow-unsupported-compiler

* trigger when build.yml changes

* another test

* try exllama/bdashore3 method

* install vs build tools before cuda toolkit

* try win-2019

ggml-ci

* fix broken link in pr template

* Update pull_request_template.md [no ci]

---------

Co-authored-by: Brian <[email protected]>

* Update Vulkan RoPE implementation

* Return nullptr on alloc_buffer when allocation fails, instead of throwing an exception

Minor fixes

* Fix segfault when running out of VRAM

Co-authored-by: slaren <[email protected]>

---------

Co-authored-by: slaren <[email protected]>

…gerganov#7582)

…#7794) [no ci]

Fix "appropiate" to "appropriate" and add Fedora 40 packages to install to compile with Vulkan support

…rganov#7894)

In addition this reverts a workaround we had to do to workaround the upstream issue with expired intel GPG package keys in 2024.0.1-devel-ubuntu22.04

* ggml : improve ggml_is_contiguous logic

ggml-ci

* ggml : support more contiguous cases

ggml-ci

* tests : add non-cont unary tests

* ggml : update unary asserts and "supports_op"

ggml-ci

…llama-llava-cli, etc... (ggerganov#7809)

* `main`/`server`: rename to `llama` / `llama-server` for consistency w/ homebrew

* server: update refs -> llama-server

gitignore llama-server

* server: simplify nix package

* main: update refs -> llama

fix examples/main ref

* main/server: fix targets

* update more names

* Update build.yml

* rm accidentally checked in bins

* update straggling refs

* Update .gitignore

* Update server-llm.sh

* main: target name -> llama-cli

* Prefix all example bins w/ llama-

* fix main refs

* rename {main->llama}-cmake-pkg binary

* prefix more cmake targets w/ llama-

* add/fix gbnf-validator subfolder to cmake

* sort cmake example subdirs

* rm bin files

* fix llama-lookup-* Makefile rules

* gitignore /llama-*

* rename Dockerfiles

* rename llama|main -> llama-cli; consistent RPM bin prefixes

* fix some missing -cli suffixes

* rename dockerfile w/ llama-cli

* rename(make): llama-baby-llama

* update dockerfile refs

* more llama-cli(.exe)

* fix test-eval-callback

* rename: llama-cli-cmake-pkg(.exe)

* address gbnf-validator unused fread warning (switched to C++ / ifstream)

* add two missing llama- prefixes

* Updating docs for eval-callback binary to use new `llama-` prefix.

* Updating a few lingering doc references for rename of main to llama-cli

* Updating `run-with-preset.py` to use new binary names.
Updating docs around `perplexity` binary rename.

* Updating documentation references for lookup-merge and export-lora

* Updating two small `main` references missed earlier in the finetune docs.

* Update apps.nix

* update grammar/README.md w/ new llama-* names

* update llama-rpc-server bin name + doc

* Revert "update llama-rpc-server bin name + doc"

This reverts commit e474ef1.

* add hot topic notice to README.md

* Update README.md

* Update README.md

* rename gguf-split & quantize bins refs in **/tests.sh

---------

Co-authored-by: HanClinto <[email protected]>

* move BLAS to a separate backend

* rename GGML_USE_OPENBLAS to GGML_USE_BLAS

* alloc : reuse same buffer when the same buffer type if used multiple times

* set number of threads automatically for openblas and blis

* sched : print assignments when GGML_SCHED_DEBUG env variable is set

* sched : allow ops with weights on an incompatible buffer type

This will cause the weight to be copied to a backend that supports the
op, which is very costly. The weight should have been stored in a buffer
of a backend that can run the op, but llama.cpp cannot do this
automatically at the moment.

---------

Co-authored-by: Georgi Gerganov <[email protected]>

… [no ci]

* support for Poro chat pre-tokenizer

* add support for Poro pre-tokenizer

* Update convert-hf-to-gguf-update.py

Co-authored-by: Georgi Gerganov <[email protected]>

* Change Poro-34B-chat to poro-chat

* Change Poro-34B-chat to poro-chat

* Update convert-hf-to-gguf-update.py

* Update llama.cpp

---------

Co-authored-by: Georgi Gerganov <[email protected]>

* More checks before assuming FIM tokens for Llama arch

* extensive token check

Show "<backend_name>+RPC" when RPC offloading is used

* CUDA: faster q2_K, q3_K MMQ + int8 tensor cores

* try CI fix

* try CI fix

* try CI fix

* fix data race

* rever q2_K precision related changes

In order to use old `macos-latest` we should use `macos-12`

Potentially will fix: ggerganov#6975

* separate DPCT helpers outside

* replace global variables with context

* remove useless extra

* update mul_mat condition

* remove duplicate buft initialization

* remove duplicate extra and global work group size

* remove useless backend check

* remove duplicated extras

* use macro for group_size and remove cuda-related

* add control-vector-generator

* calc diff

* add comments

* proof-of-concept stdlib implementation

Implements PCA and file writing using mostly standard libraries. The output is recognized as a functional control vector, but outputs gibberish.

* param parsing, refactor, comments

Added basic command-line parameters for outfile and one each positive/negative prompt.

Refactored some messy code in PCA computation and GGUF exporting.

Left a bunch of comments regarding further work needed.

* example template completions

Implements an example template set built from the positive/negative prompts like the control vector Python implementation.

* add multi prompts, multi-thread for PCA

* fix mem error

* add debugs

* fix matrix transpose multiplication

you have got to be kidding me

* preliminary template/multiprompt support

model is running out of context and that ought to be fixed (segfaulting) but other than that it looks goodish

* fix zero output & param parsing, functional templating

fixed a bug where the output file had no tensor data/was all zero

fixed a bug where single hyphen flags were not being correctly parsed

implements creation of templated prompts from input (still need to adapt based on model)

* fix square_diff matmul index range and CRLF->LF line endings

fixed a logic error where square_diff would not multiply all rows

fixed a formatting error where the provided completions.txt had CRLF line endings

* add command-line args for num threads, num completions file lines, always reload model

refactored a few things and did what the commit message says on the tin

* code aestheticization

* fix compiler warnings

* in-series multithreading for prompt embedding?

added commented-out code to attempt to start implementing mutlithreading for embedding in main

* remove unnecessary multithreading

* interim fix memory leak

* translated everything but PCA (I think)

* tentatively translate the rest

* fix ggml errors and make new ones

at least it compiles and runs

* fix cb_eval

* temporary commit while I move dev environments

it finally outputs a functioning control vector - "functioning" in the sense that it can be loaded and it clearly has the right idea, but makes the model incoherent

* update debug statements

* pre-tokenize so we can allocate correct memory to ctx_diffs_wrapped

* update comments

* (wip) refactor

* clean up PCA ggml implementation

* fix shape of v_diff_original

* add n_batch for pca

* working version

* remember to copy back the last_eigenvector

* fix n_completions

* bring back n_completions

* default n_pca_batch to 20

* fix macos build

* add to makefile all targets

* use ggml_format_name

* add readme

* fix .editorconfig

* use ggml_backend_tensor_copy

* attemp to fix compile problem on mac

* fix compile warn

* reuse allocr

* move param parser to common

* better error handling

* clean up a bit

* add print_usage

* shorten help msg

* beautify help msg

* escape prompt by default

* change compile target to llama-cvector-generator

* typo

* disable GPU for PCA

* code style

---------

Co-authored-by: Christian Zhou-Zheng <[email protected]>

* Refactor shaders, extract GLSL code from ggml_vk_generate_shaders.py into vulkan-shaders directory

* Improve debug log code

* Add memory debug output option

* Fix flake8

* Fix unnecessary high llama-3 VRAM use

ggml-ci

ggml-ci

Signed-off-by: Daniel Bevenius <[email protected]>

* fix compile issues introduced by loongarch_asx

* restore quant changes to merge

* fix compile issues introduced by loongarch_asx

* further optimize by using vec_msum & vec_sum4s on ppc64le

* cuda : fix bounds check for src0 rows in MMVQ kernel

* Update ggml-cuda/mmvq.cu

Co-authored-by: Johannes Gäßler <[email protected]>

---------

Co-authored-by: Johannes Gäßler <[email protected]>

* cuda sqrt support

* enable cuda in pca

* fix comments in pca

* add test

* add sqrt to ggml_backend_cuda_supports_op

* fix test

* new line

* Use F32 sqrtf instead of F64 sqrt

Co-authored-by: Johannes Gäßler <[email protected]>

---------

Co-authored-by: Johannes Gäßler <[email protected]>

…ews" (ggerganov#7946)

* Update README-sycl.md

* Update README-sycl.md

* Update README-sycl.md

* Update README-sycl.md

* gguf-dump.py: add --markdown dump output

* gguf-dump.py: Add toc

* gguf-dump.py: use standard tensor name lookup. Also add tensor ID field

* gguf-dump.py: Add tensor overview count

* gguf-dump.py: fix array preview

* gguf-dump.py: markdownTableWithAlignmentSupport() added

* Add type hints and spacing

Co-authored-by: compilade <[email protected]>

* gguf-dump.py: prettyfy dimention

* gguf-dump: right align element count

* gguf-dump.py: element count autosizing

* Apply suggestions from code review

Co-authored-by: compilade <[email protected]>

---------

Co-authored-by: compilade <[email protected]>

* Implement non-mapped async IO for CUDA on Windows. On a fast Gen5 NVMe drive this change improves model load time by >3x while it should be the same (or slightly faster) on any other drive.

* Free resources except for backend.

* Change assertions to exceptions in llama_file, find correct cuda backend to create CUDA resources and respect the use_mmap flag again for CUDA.

* Apply suggestions from code review

Co-authored-by: slaren <[email protected]>

* Fix editorconfig and unused variable

* Fix issues with Windows build

---------

Co-authored-by: slaren <[email protected]>

Signed-off-by: thxCode <[email protected]>

…7851)

* update: convert-hf-to-gguf.py to support Qwen2-57B-A14B

* fix: QWEN2MOE support for expert_feed_forward_length

previously, expert ff was taken from n_ff (intermediate size) but it is now properly taken from LLM_KV_EXPERT_FEED_FORWARD_LENGTH

n_ff_exp and n_ff_shared_exp are now properly calculated

* update: convert-hf-to-gguf.py cleanup for Qwen2MoeForCausalLM

* fix: QWEN2MOE support for expert_feed_forward_length

previously, expert ff was taken from n_ff (intermediate size) but it is now properly taken from LLM_KV_EXPERT_FEED_FORWARD_LENGTH

n_ff_exp and n_ff_shexp are now properly calculated

* whisper : use ggml_backend_sched (wip)

* use sched in whisper_allocr

* whisper : single backend in whisper_context

* whisper : remove whisper_state->backends_used

* whisper : remove whisper_context->backend

* whisper : reset scheduler after init

* whisper : fix external encoder (e.g. CoreML)

* whisper : cleanup

* whisper : handle null GPU buffer types + fix sycl

---------

Co-authored-by: slaren <[email protected]>