Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

merge upstream #42

Merged
merged 34 commits into from
Oct 10, 2024
Merged

merge upstream #42

merged 34 commits into from
Oct 10, 2024

Conversation

l3utterfly
Copy link
Owner

OuadiElfarouki and others added 30 commits October 3, 2024 07:50
@OuadiElfarouki
Fixed dequant precision issues in Q4_1 and Q5_1 (ggerganov#9711)
5639971
@rgerganov
rpc : enable vulkan (ggerganov#9714)
841713e 
closes ggerganov#8536
@compilade
convert : handle tokenizer merges format from transformers 4.45 (gger…
e3c355b 
…ganov#9696)
@bandoti
ggml: unify backend logging mechanism (ggerganov#9709)
d6fe7ab 
* Add scaffolding for ggml logging macros

* Metal backend now uses GGML logging

* Cuda backend now uses GGML logging

* Cann backend now uses GGML logging

* Add enum tag to parameters

* Use C memory allocation funcs

* Fix compile error

* Use GGML_LOG instead of GGML_PRINT

* Rename llama_state to llama_logger_state

* Prevent null format string

* Fix whitespace

* Remove log callbacks from ggml backends

* Remove cuda log statement
@slaren
ggml-backend : add device description to CPU backend (ggerganov#9720)
a7ad553
@jmousseau
metal : fix compute pass descriptor autorelease crash (ggerganov#9718)
5d5ab1e
@JohannesGaessler @ggerganov
ggml: refactor cross entropy loss CPU impl. (ggml/976)
eee39bd
@JohannesGaessler @ggerganov
ggml/ex: calculate accuracy in graph, adapt MNIST (ggml/980)
fabdc3b
@ggerganov
sync : ggml
1bb8a64
@ggerganov
metal : remove abort (skip) (ggml/0)
d5ed2b9
@d-kleine
Fixed RNG seed docs (ggerganov#9723)
133c7b4 
* Update README.md

fixed RNG seed info

* changed print format to unsigned
@ngxson
ci : fine-grant permission (ggerganov#9710)
f3fdcfa
@slaren @ggerganov
ggml : fixes after sync (ggml/983)
ff56576 
ggml : remove test-backend-buffer

ggml : fix CUDA build warnings
@danbev @ggerganov
ggml : fix typo in example usage ggml_gallocr_new (ggml/984)
55951c0
@ggerganov
sync : ggml
1788077
@vietanhdev
Add Llama Assistant (ggerganov#9744)
71967c2
@ggerganov
metal : zero-init buffer contexts (whisper/0)
905f548
@ggerganov
sync : ggml
58b1669
@ggerganov
rerank : use [SEP] token instead of [BOS] (ggerganov#9737)
8c475b9 
* rerank : use [SEP] token instead of [BOS]

ggml-ci

* common : sanity check for non-NULL tokens

ggml-ci

* ci : adjust rank score interval

ggml-ci

* ci : add shebang to run.sh

ggml-ci
@SRHMorris @ggerganov
vulkan : retry allocation with fallback flags (whisper/2451)
b0915d5 
Co-authored-by: Samuel Morris <[email protected]>
@ggerganov
sync : llama.cpp
b6d6c52
@ggerganov
readme : fix typo [no ci]
f4b2dcd
@ggerganov
contrib : simplify + minor edits [no ci]
d5cb868
@ptsochantaris @ggerganov
metal : single allocation of encode_async block (ggerganov#9747)
96b6912 
* Single allocation of encode_async block with non-ARC capture in ggml-metal.m

* Moving Block_release to the deallocation code

* Release encode block when re-setting encoding buffer count if needed

* Update ggml/src/ggml-metal.m

---------

Co-authored-by: Georgi Gerganov <[email protected]>
@ggerganov @slaren
ggml : add metal backend registry / device (ggerganov#9713)
d5ac8cf 
* ggml : add metal backend registry / device

ggml-ci

* metal : fix names [no ci]

* metal : global registry and device instances

ggml-ci

* cont : alternative initialization of global objects

ggml-ci

* llama : adapt to backend changes

ggml-ci

* fixes

* metal : fix indent

* metal : fix build when MTLGPUFamilyApple3 is not available

ggml-ci

* fix merge

* metal : avoid unnecessary singleton accesses

ggml-ci

* metal : minor fix [no ci]

* metal : g_state -> g_ggml_ctx_dev_main [no ci]

* metal : avoid reference of device context in the backend context

ggml-ci

* metal : minor [no ci]

* metal : fix maxTransferRate check

* metal : remove transfer rate stuff

---------

Co-authored-by: slaren <[email protected]>
@ggerganov @github-actions
flake.lock: Update (ggerganov#9753)
6279dac 
Flake lock file updates:

• Updated input 'flake-parts':
    'github:hercules-ci/flake-parts/bcef6817a8b2aa20a5a6dbb19b43e63c5bf8619a?narHash=sha256-HO4zgY0ekfwO5bX0QH/3kJ/h4KvUDFZg8YpkNwIbg1U%3D' (2024-09-12)
  → 'github:hercules-ci/flake-parts/3d04084d54bedc3d6b8b736c70ef449225c361b1?narHash=sha256-K5ZLCyfO/Zj9mPFldf3iwS6oZStJcU4tSpiXTMYaaL0%3D' (2024-10-01)
• Updated input 'flake-parts/nixpkgs-lib':
    'https://github.com/NixOS/nixpkgs/archive/356624c12086a18f2ea2825fed34523d60ccc4e3.tar.gz?narHash=sha256-Ss8QWLXdr2JCBPcYChJhz4xJm%2Bh/xjl4G0c0XlP6a74%3D' (2024-09-01)
  → 'https://github.com/NixOS/nixpkgs/archive/fb192fec7cc7a4c26d51779e9bab07ce6fa5597a.tar.gz?narHash=sha256-0xHYkMkeLVQAMa7gvkddbPqpxph%2BhDzdu1XdGPJR%2BOs%3D' (2024-10-01)
• Updated input 'nixpkgs':
    'github:NixOS/nixpkgs/1925c603f17fc89f4c8f6bf6f631a802ad85d784?narHash=sha256-J%2BPeFKSDV%2BpHL7ukkfpVzCOO7mBSrrpJ3svwBFABbhI%3D' (2024-09-26)
  → 'github:NixOS/nixpkgs/bc947f541ae55e999ffdb4013441347d83b00feb?narHash=sha256-NOiTvBbRLIOe5F6RbHaAh6%2B%2BBNjsb149fGZd1T4%2BKBg%3D' (2024-10-04)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
@amqdn
Update building for Android (ggerganov#9672)
f1af42f 
* docs : clarify building Android on Termux

* docs : update building Android on Termux

* docs : add cross-compiling for Android

* cmake : link dl explicitly for Android
@slaren
ggml : add backend registry / device interfaces to BLAS backend (gger…
6374743 
…ganov#9752)

* ggml : add backend registry / device interfaces to BLAS backend

* fix mmap usage when using host buffers
@standby24x7
scripts : fix spelling typo in messages and comments (ggerganov#9782)
fa42aa6 
Signed-off-by: Masanari Iida <[email protected]>
@ngxson
server : better security control for public deployments (ggerganov#9776)
458367a 
* server : more explicit endpoint access settings

* protect /props endpoint

* fix tests

* update server docs

* fix typo

* fix tests
slaren and others added 4 commits October 8, 2024 14:21
@slaren
ggml : fix BLAS with unsupported types (ggerganov#9775)
dca1d4b 
* ggml : do not use BLAS with types without to_float

* ggml : return pointer from ggml_internal_get_type_traits to avoid unnecessary copies

* ggml : rename ggml_internal_get_type_traits -> ggml_get_type_traits

it's not really internal if everybody uses it
@ggerganov
examples : remove llama.vim
3dc48fe 
An updated version will be added in ggerganov#9787
@ggerganov
perplexity : fix integer overflow (ggerganov#9783)
e702206 
* perplexity : fix integer overflow

ggml-ci

* perplexity : keep n_vocab as int and make appropriate casts

ggml-ci
@slaren
cmake : do not build common library by default when standalone (ggerg…
c81f3bb 
…anov#9804)
@l3utterfly l3utterfly merged commit 2f7d58e into layla-build Oct 10, 2024
72 of 85 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
android Apple Metal build devops documentation Improvements or additions to documentation examples ggml nix Nvidia GPU python script server SYCL testing Vulkan
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.