Adds a SetMaxSeqLen method to ModelConfig to handle updating both max_seq_len and global attention window sizes. The Gemma constructor now checks if the provided inference seq_len exceeds the model's max_seq_len and, if so, emits a warning and updates the config.
This prevents clipping context to the hard-coded maximum.
PiperOrigin-RevId: 853676074
Creates new cc_library targets for :attention, :tensor_stats and :activations. Eliminates cyclic dependencies between these libraries.
PiperOrigin-RevId: 845690136
This catches typos/incorrect usage.
Refactor: group Loader/Threading/Inference into GemmaArgs.
All *Args ctors now have an extra ConsumedArgs& argument.
PiperOrigin-RevId: 844690553
Moves query-related structs/classes to gemma/query.h.
This refactors PerQuery, AllQueries, and QBatch into a dedicated header file, gemma/query.h, and updates BUILD dependencies accordingly.
PiperOrigin-RevId: 843604293
(1) A function GenerateTWithContinuousBatching is added to use continuous batching when enabled.
(2) The ContinuousQBatch is added as a subclass of QBatch to manage prefill, insert, used-kv-cache-collection.
(3) Also expanded the unit test to more diverse cases.
PiperOrigin-RevId: 836090261
Uses the key_norm and query_norm layers to disambiguate between the Gemma2-2B and Gemma3-1B models.
Since Gemma3-1B is not multimodal, ViT is not an effective disambiguator. KQ normalization is a structural disambiguator between gemma2 and gemma3.
PiperOrigin-RevId: 833213331
This could lead to stack overflow in B_storage.
Also do not require specific type for query_norm_scale,
update batch sizes for attention tensors,
more verbose Mat shape/type checks.
PiperOrigin-RevId: 824987689
* Adds and uses a new `AttentionActivationPtrs` that holds non-owning `MatPtrs`. Acts as a view into `AttentionActivations`.
* Updates `QBatch` to hold non-owning `MatPtr`s to the kv caches.
* Enables the `MatPtrT` default constructor for simpler initializations.
* Pulls out and passes `LayerWeightsPtrs::query_norm_scale` directly. While `LayerWeightsPtrs` already held non-owning `MatPtr`s, this change avoids the need to find and construct several empty weight tensors just to construct one `query_norm_scale` tensor.
PiperOrigin-RevId: 824584177
Pass ThreadingContext instead of Pools/Profiler individually, for access to Zones
Add GCPP_ZONE helper
Add Caller argument to pool.Run to enable new stats
Remove most direct dependencies on ThreadPool, prefer ParallelFor
PiperOrigin-RevId: 822934530
Balazs Racz
Krzysztof Rymski
Jan Wassenberg
Phil Culliton
Martin Stolle
Charles Zhao
The gemma.cpp Authors
Ray Smith
Biruk Mammo
Theotime Combes