This CL adds a new function to Gemma that allows for batching of multiple prompts. The function takes a vector of prompts and returns a vector of responses. The prompts are processed in parallel, and the responses are returned in the same order as the prompts.
PiperOrigin-RevId: 648367559
Helper functions to tokenize/wrap
Move LayersOutputFunc into RuntimeConfig
AcceptFunc passes the probability
Implement StringFromType using the parser, and verify results match
PiperOrigin-RevId: 643255119
accept_token: allow default, check if empty when using
allow mixing sample_func and stream_func, call the latter after the former
Also fix missing includes/deps.
PiperOrigin-RevId: 642240012
This changes the command line flags, but the default value retains the previous behavior.
Also add a CreateGemma helper to enable extra args without interface changes.
PiperOrigin-RevId: 641266411
With this addition the ComputeCrossEntropy function can be moved
to its own library, because now we can compute it using only the
public API functions from gemma.h
Split common and weights into separate lib
Remove common-inl (does not have to be SIMD code), activations.cc
Centralize switch(Model) to avoid duplication
Move CompressWeightsT to compress_weights.cc
Move LoadWeights to weights.cc
PiperOrigin-RevId: 640869202
Move Path into io.h and use for opening files.
Removes dependency of gemma_lib on args.
Separate Windows codepath instead of emulating POSIX functions.
Plus lint fixes.
PiperOrigin-RevId: 626279004
Also add a script to help running sanitizer builds, and do some cleanup.
Co-authored-by: Andrey Mikhaylov <amik@google.com>
Co-authored-by: Eugene Kliuchnikov <eustas@google.com>
Co-authored-by: Sami Boukortt <sboukortt@google.com>
Co-authored-by: Zoltan Szabadka <szabadka@google.com>
--
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
--
19694e1f2e by Silvio Traversaro <silvio@traversaro.it>:
Do not pass explicitly -O2 flag to compiler in Release build
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/gemma.cpp/pull/3 from traversaro:patch-1 19694e1f2e
PiperOrigin-RevId: 610096914
* Rename BUILD to BUILD.bazel.
This fixes an error on macOS due to `build` and `BUILD` having conflicting names.
* Enable macos-latest in GitHub Actions CI.
* Fix concurrency key in GitHub Actions.
Use matrix configuration in concurrency key.
Jan Wassenberg
The gemma.cpp Authors
Paul Chang
Andrey Vlasov
Ray Smith
Daniel Keysers
Zoltan Szabadka
Copybara-Service
Zelalem Aweke
Apoorv Reddy
Andrey Mikhaylov
Luca Versari
Eric Ye
Austin Huang
Dan Zheng
Silvio Traversaro