happyz
/
gemma.cpp
mirror of https://github.com/google/gemma.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
136 Commits 19 Branches 5 Tags 35 MiB
Commit Graph

136 Commits

Author SHA1 Message Date
austinvhuang e781007836 [WIP] Remove InferenceArgs from hello_world example, fix ordering of LoaderArgs validation, revert ReplGemma EOT token behavior 2024-03-06 23:21:13 -05:00
austinvhuang 7042316013 [WIP] update GemmaInterface, Gemma, and Generate input parameter specs to remove InferenceArgs. TODO: update hello_world example after git commit hash is available for fetching 2024-03-06 22:22:59 -05:00
austinvhuang 0f6a4b49d5 [WIP] quality tweaks - for constants, defer float cast and use double for intermediate computations, add `model` to EOT token 2024-03-06 15:34:11 -05:00
austinvhuang 5b9d8a9936 [WIP] dev/examples branch merge 2024-03-06 15:10:48 -05:00
austinvhuang 10f7a086aa [WIP] decouple GemmaImpl from CLI args 2024-03-06 15:06:41 -05:00
Jan Wassenberg 3cdd5e524a Fix loop iteration in GeluMulToBF16 
Also attempt to speed up builders (parallel)

PiperOrigin-RevId: 613092863
 2024-03-05 23:00:47 -08:00
enum-class 843d9b0e1f fix for-loop bounderies 2024-03-06 08:25:50 +08:00
Copybara-Service c8b9675898 Merge pull request #74 from osanseviero:patch-1 
PiperOrigin-RevId: 612937722
 2024-03-05 12:49:09 -08:00
Phil Culliton c93e1a1e4d Resolved layer ordering, reshaping, MQA->MHA, and quantization. Works only for 2B. 2024-03-05 17:54:55 +00:00
enum-class bc845515b7 fix style, add kCamelCase style for constexpr in clang-tidy 2024-03-05 20:45:30 +08:00
enum-class 5f016fb433 use hwy/simd for RMSNorm(f, bf, f) calculation 2024-03-05 17:53:52 +08:00
enum-class 507d64e3e6 use hwy/simd for SquaredL2 calculation 2024-03-05 17:37:09 +08:00
Jan Wassenberg bb9b023502 Support Bazel builds. Fixes #16 
Also fix nuq/sfp-inl: warning, cast, and disable SCALAR

PiperOrigin-RevId: 612704056
 2024-03-04 22:07:25 -08:00
Omar Sanseviero 8c857b957e
Update README.md 2024-03-04 12:58:49 +01:00
Copybara-Service cd7468199c Merge pull request #65 from enum-class:narrowing-issues 
PiperOrigin-RevId: 612279564
 2024-03-03 18:51:59 -08:00
austinvhuang c378ac2c56 [WIP] hello world example working. TODO: refactor interfaces to decouple arguments 2024-03-03 11:36:48 -05:00
austinvhuang 39cd59caec [WIP] create skeleton for example frontend application 2024-03-03 10:33:29 -05:00
enum-class 90c99c330d use hwy::SignedFromSize traits 2024-03-03 10:56:46 +08:00
austinvhuang 3c69695c1e transformations and validations (wip) 2024-03-02 14:46:51 -05:00
austinvhuang 7d7d43e661 converter transformations (wip) 2024-03-02 08:11:55 -05:00
Omar Sanseviero 86761dc113
Update README.md 2024-03-01 23:44:38 +01:00
austinvhuang 5be9a2243f initial (wip) convert_weights script from pytorch 2024-03-01 15:52:51 -05:00
Copybara-Service 808dbdc42b Merge pull request #71 from google:docs 
PiperOrigin-RevId: 611785397
 2024-03-01 06:04:51 -08:00
austinvhuang b841620d6b add using gemma as a library notes to DEVELOPERS 2024-02-29 23:52:59 -05:00
Paul Chang ae7901c3f4 Minor style fix 
Remove some obsolete TODOs.

PiperOrigin-RevId: 611571224
 2024-02-29 13:08:26 -08:00
enum-class 626be6deab add StaticCast 2024-02-29 21:00:54 +08:00
Jan Wassenberg b6aaf6bbb8 Fix for Android's 32-bit off_t. Fixes #62 
PiperOrigin-RevId: 611249534
 2024-02-28 15:30:19 -08:00
Copybara-Service c805fbe780 Merge pull request #66 from google:dev-cleanup 
PiperOrigin-RevId: 611207602
 2024-02-28 13:22:46 -08:00
austinvhuang 0ea7b993de remove --log fixing https://github.com/google/gemma.cpp/issues/59, improve command line args help, add copybara #include sort guards in more source files, add README sections on running faster and related projects 2024-02-28 15:18:40 -05:00
Jan Wassenberg 272f17ddb3 Warning fixes: unused member, cast, unused function 
PiperOrigin-RevId: 611074887
 2024-02-28 05:54:22 -08:00
enum-class 06dd013397 Add clang-tidy, fix narrowing issues, fix constness 2024-02-28 20:04:09 +08:00
Copybara-Service f4a14bfdf2 Merge pull request #58 from google:dev-cleanup 
PiperOrigin-RevId: 610942948
 2024-02-27 18:47:38 -08:00
austinvhuang 060c8862dd whitespace cleanup 2024-02-27 21:36:43 -05:00
austinvhuang d37f9c3604 re-enable SortIncludes to conform to vanilla Google style, add comment lines to #includes in gemma.h as barriers to block destructive sorting, update doc + remove shell script 2024-02-27 21:23:33 -05:00
austinvhuang 8f3bd63bf7 Fix copybara include path substitutions errors (which break the google3 build) arising from clang-format linter automation 2024-02-27 17:11:15 -05:00
austinvhuang f70d2de16f use `style=Google` - dumped for .clang-format, gemma.h updated 2024-02-27 15:44:03 -05:00
Copybara-Service 1a1dd90287 Merge pull request #33 from shirayu:add_eot_option 
PiperOrigin-RevId: 610838070
 2024-02-27 12:32:01 -08:00
Dan Zheng 874deee302
Update DEVELOPERS.md 2024-02-27 11:32:33 -08:00
austinvhuang 9cdc9223bc clean up formatting after 129e66ada2, add .clang-format defaults, minor updates to DEVELOPERS doc 2024-02-27 14:22:02 -05:00
Jan Wassenberg 179ecf9e78 Warn instead of assert for setaffinity. Fixes #49 
PiperOrigin-RevId: 610638517
 2024-02-26 22:46:11 -08:00
Jan Wassenberg b3fecef45d Warning fix: sign cast 
PiperOrigin-RevId: 610635789
 2024-02-26 22:31:39 -08:00
Dan Zheng afc354dcb1 Import from GitHub. 
PiperOrigin-RevId: 610595796
 2024-02-26 19:05:11 -08:00
Dan Zheng 8db89304bd No public description 
PiperOrigin-RevId: 610498969
 2024-02-26 19:03:48 -08:00
austinvhuang 129e66ada2 Reduce KV cache preallocation to 4096 and make it comptime configurable, add rm build note in readme, add note on comptime options in DEVELOPERS, make multiturn=0 the default 2024-02-26 17:05:32 -05:00
David Coles 7aeade5c9d Copybara import of the project: 
--
c64b6fd3a44b385e1502d2057bd8709edaebaa58 by David Coles <dcoles@dcoles.net>:

Include Windows in GitHub Actions build

This also preserves the `gemma` binary as a build artefact
should folks want to grab a pre-built binary.

Dropped the use of the lukka/cmake actions due to conflicts with `--preset`.
This isn't that bad as we were mostly overriding the default behaviour anyway.

It also shaves ~2 min off the build since the GitHub builders already
have CMake pre-installed.

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/gemma.cpp/pull/38 from dcoles:windows-build c64b6fd3a44b385e1502d2057bd8709edaebaa58
PiperOrigin-RevId: 610449220
 2024-02-26 10:22:57 -08:00
Naoki Kishida 7ab968c957 Copybara import of the project: 
--
26b541b666 by kishida <naokikishida@gmail.com>:

add information for the reseting conversation

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/gemma.cpp/pull/40 from kishida:add_info_for_reset_conv 26b541b666
PiperOrigin-RevId: 610418671
 2024-02-26 08:39:27 -08:00
Kewde 4e2efbcbd8 Copybara import of the project: 
--
f4f2ff3c1a by kewde <kewde@particl.io>:

fix: add -fPIC to libgemma
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/gemma.cpp/pull/42 from kewde:kewde/enable-fpic f4f2ff3c1a
PiperOrigin-RevId: 610416597
 2024-02-26 08:31:06 -08:00
Dan Zheng 4c155bd3df Restore reverted changes. 
Sync to 84444c93a4.

PiperOrigin-RevId: 610263918
 2024-02-25 19:32:07 -08:00
Jan Wassenberg 6a3085828f Fixes #37, lambda issue: missing HWY_ATTR, and cannot capture SVE in/out vectors. 
PiperOrigin-RevId: 610260610
 2024-02-25 19:09:13 -08:00
Dan Zheng 1243be71c4 Copybara import of the project: 
--
e0179bad83 by Dan Zheng <danielzheng@google.com>:

Rename BUILD to BUILD.bazel.

This fixes an error on macOS due to `build` and `BUILD` having conflicting names.

--
74b27074e1 by Dan Zheng <danielzheng@google.com>:

Enable macos-latest in GitHub Actions CI.

--
c08de58e6a by Dan Zheng <danielzheng@google.com>:

Fix concurrency key in GitHub Actions.

Use matrix configuration in concurrency key.

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/gemma.cpp/pull/36 from dan-zheng:rename-build-bzl b4b978f02b
PiperOrigin-RevId: 610156681
 2024-02-25 04:34:15 -08:00