happyz
/
gemma.cpp
mirror of https://github.com/google/gemma.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
897 Commits 11 Branches 5 Tags 38 MiB
Commit Graph

175 Commits

Author SHA1 Message Date
Krzysztof Rymski 539d9bb8e7 Change to use faster exponent function 
PiperOrigin-RevId: 877981568
 2026-03-03 09:16:04 -08:00
Ray Smith 49cb438b1e Rollback of erroneous rollback. 
PiperOrigin-RevId: 877376165
 2026-03-02 06:50:26 -08:00
The gemma.cpp Authors a3d994915f No public description 
PiperOrigin-RevId: 877333188
 2026-03-02 04:32:29 -08:00
Ray Smith 16c1b29b89 Rewrote flash attention to use BF16, transpose k and v, rewrote the task distribution, increase parallelism on decode, and use double the registers for the core of flash attention. 
PiperOrigin-RevId: 877308306
 2026-03-02 03:11:01 -08:00
Nikhil Dev Goyal dd268ddbe8 Add FastGelu activation function in a newly created created fast_ops-inl.h files. 
This replaces the Tanh call with FastTanh call in the Gelu function written in math-inl.h.

PiperOrigin-RevId: 876339830
 2026-02-27 11:14:47 -08:00
Krzysztof Rymski df162ead7c Implementation of tiled attention with bf16 and circular buffers which reduces memory requirements by 4x on longer context on gemma models. 
It also supports better parallelism for small batch sizes / small models.
It also is able to utilize VDPBF16PS for nice 2x improvement on avx512

PiperOrigin-RevId: 874517319
 2026-02-24 03:26:49 -08:00
Ray Smith 76d7951242 Added wheat_from_chaff_test to test the ability of a model to find a needle in a haystack of data. 
Replaced flag with attention_impl to control which attention to run.

PiperOrigin-RevId: 869694868
 2026-02-13 06:05:30 -08:00
Krzysztof Rymski 16a7ba2d6e Internal changes 
PiperOrigin-RevId: 854171429
 2026-01-09 06:35:36 -08:00
Krzysztof Rymski 2ee1fac74c Internal changes 
PiperOrigin-RevId: 853138600
 2026-01-07 01:21:37 -08:00
Krzysztof Rymski b73a9ede8f Internal changes 
PiperOrigin-RevId: 846648337
 2025-12-19 02:46:18 -08:00
Krzysztof Rymski 6661d3a60c Internal changes 
PiperOrigin-RevId: 846140314
 2025-12-18 01:26:43 -08:00
Liam Miller-Cushon 142e6a7e9c No public description 
PiperOrigin-RevId: 846030124
 2025-12-17 20:10:54 -08:00
Balazs Racz 596bdfe5af Separate monolithic gemma_lib library into more specific cc_library targets. 
Creates new cc_library targets for :attention, :tensor_stats and :activations. Eliminates cyclic dependencies between these libraries.

PiperOrigin-RevId: 845690136
 2025-12-17 03:31:16 -08:00
Balazs Racz baa69dfb78 Makes the entire runtime_config passed into the activations constructor. 
PiperOrigin-RevId: 845153671
 2025-12-16 01:56:52 -08:00
Krzysztof Rymski 44dfd69b9b Internal changes 
PiperOrigin-RevId: 844759322
 2025-12-15 07:14:37 -08:00
Jan Wassenberg 0c64987a96 Abort if args are unrecognized, refactor argument passing 
This catches typos/incorrect usage.
Refactor: group Loader/Threading/Inference into GemmaArgs.
All *Args ctors now have an extra ConsumedArgs& argument.
PiperOrigin-RevId: 844690553
 2025-12-15 03:18:45 -08:00
Balazs Racz 338cd8a36e Factors out a new cc_library `:query` from `:gemma-lib`. 
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
 2025-12-12 02:53:56 -08:00
Jan Wassenberg 73c3627b67 Add tensor stats and output 
tensor_info: add missing header
io: fix mode
weights.h: add layer_idx to LayerWeightsPtrs
PiperOrigin-RevId: 843531051
 2025-12-11 22:52:46 -08:00
Krzysztof Rymski 64178ace38 Internal changes 
PiperOrigin-RevId: 842727112
 2025-12-10 07:55:17 -08:00
Martin Stolle 1014ae9e2a Adding a simple test for GemmaAttention 
PiperOrigin-RevId: 842135414
 2025-12-09 02:13:03 -08:00
Jan Wassenberg 5a6895c609 Avoid warning when OS affinity limits us to the second socket 
Also simplify NumSMT, detect from .smt field directly

PiperOrigin-RevId: 841749486
 2025-12-08 07:10:43 -08:00
Martin Stolle 9348048885 Clean up toPtrs to delegate to toPtr 
PiperOrigin-RevId: 840214969
 2025-12-04 06:22:04 -08:00
Krzysztof Rymski 2b4436beb6 Internal changes 
PiperOrigin-RevId: 840151004
 2025-12-04 02:37:53 -08:00
Jan Wassenberg ccb49bc82f Add ToFloatSlow, move RandomFloat to test_util 
PiperOrigin-RevId: 837412290
 2025-11-27 00:14:51 -08:00
Krzysztof Rymski c153d5255b Internal changes 
PiperOrigin-RevId: 837001762
 2025-11-26 01:05:35 -08:00
Martin Stolle 35e9f9f05f Introduce attention implementation configurability. 
PiperOrigin-RevId: 828971705
 2025-11-06 08:43:41 -08:00
Ray Smith 8a100c1e8d Added access to flash attention internals to TileFlashAttention4 
PiperOrigin-RevId: 826011137
 2025-10-30 06:50:05 -07:00
Biruk Mammo 5a05857deb [Gemma.cpp] Allows non-owned arguments for attention methods. 
* 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
 2025-10-27 10:43:25 -07:00
Jan Wassenberg 3ed403e287 Major cleanup of profiler zones, add Caller annotation for all pool.Run 
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
 2025-10-23 01:54:24 -07:00
Phil Culliton 503aaddd65 Add 8-bit integer quantization (I8Stream) to Gemma.cpp. 
PiperOrigin-RevId: 819787856
 2025-10-15 09:25:20 -07:00
Ray Smith fb6fa793f4 Added a global (to gemma) zones list to enable most call sites to PROFILER_ZONE3 to avoid the sychronization required for the static const initialization of the zone handle. 
Improved flash_attention to enable profiling using the new zones.

PiperOrigin-RevId: 819235421
 2025-10-14 08:30:58 -07:00
Jan Wassenberg 035273c184 tune pool kSpin mode in threading_context 
Previously, this happened concurrently with the matmul autotune, which could lead to incorrect outcomes.

threading: de-singleton Pinning (no longer stores affinity); pass PoolWorkerMapping; fix Pool dtor order
Also enable SPR target (Zen4 is AMD-only),
update Highway version for renamed Thread()->GlobalIdx().
PiperOrigin-RevId: 816223017
 2025-10-07 08:36:26 -07:00
Ray Smith 2f6cbde8ff Added a smaller tile size to flash attention for smaller batch sizes 
PiperOrigin-RevId: 813226193
 2025-09-30 05:49:20 -07:00
Jan Wassenberg fac8aac4cb Internal change 
PiperOrigin-RevId: 809975026
 2025-09-22 05:37:03 -07:00
Jan Wassenberg 501fdf000e Remove no longer used MatVec 
PiperOrigin-RevId: 809059409
 2025-09-19 09:03:22 -07:00
Ray Smith f10ac41a20 Added flash attention, with both a single-q function, and a register-tiled function. 
The register-tiled version achieves a speed-up by a factor of about 9.7 over the previous attention function on an AVX3-enabled machine.

PiperOrigin-RevId: 804913784
 2025-09-09 08:05:26 -07:00
Jan Wassenberg 461a9c7d1b Matmul refactoring towards fusion 
MMLoops: move dispatch code out, use overloads
split build target into matmul_env (for MatMulEnv/MMOptions)
weights: no longer call BindB
Fix potential out of bounds in gemma_batch_bench
PiperOrigin-RevId: 804895985
 2025-09-09 07:13:38 -07:00
Jan Wassenberg 2b4c16e243 Remove Griffin support 
Also add IsObsolete helper

PiperOrigin-RevId: 803376921
 2025-09-05 02:35:40 -07:00
Jan Wassenberg 5d1693e806 Internal change 
PiperOrigin-RevId: 803083229
 2025-09-04 10:31:20 -07:00
Jan Wassenberg afd82376a5 Add AES-CTR RNG for parallel sampling (not yet used) 
PiperOrigin-RevId: 802991142
 2025-09-04 05:58:42 -07:00
Jan Wassenberg 1e3c853e80 Add ParallelFor wrapper function and one new mode 
Move ParallelismType from matmul.h to threading.h
Replace SmallParallelFor with ParallelFor and the new mode

PiperOrigin-RevId: 802038452
 2025-09-02 01:40:09 -07:00
Jan Wassenberg 229bd078a1 1.29x speedup: bf16 C1/C2. Extend most ops to any type, expand test coverage. 
Also increase dot_test.cc range for Zen4, and matmul_test tolerance (failing in some configs)

PiperOrigin-RevId: 801789922
 2025-09-01 06:34:04 -07:00
Jan Wassenberg 5411fd846d Minor: batched NotifyGenerate, fix comment/dep 
PiperOrigin-RevId: 799889802
 2025-08-26 23:33:17 -07:00
Jan Wassenberg faa4102992 (Resubmit) Prepare profiler annotations for new API 
Pass hwy::Profiler& to low-level functions.
Used ThreadingContext arg instead of NestedPools.
Use new PROFILER_ZONE3.

PiperOrigin-RevId: 794461159
 2025-08-13 01:38:24 -07:00
The gemma.cpp Authors a2d9133f7d Prepare profiler annotations for new API 
Pass hwy::Profiler& to low-level functions.
Used ThreadingContext arg instead of NestedPools.
Use new PROFILER_ZONE3.

PiperOrigin-RevId: 793865287
 2025-08-11 17:51:38 -07:00
Jan Wassenberg 4cbf63e6f0 Prepare profiler annotations for new API 
Pass hwy::Profiler& to low-level functions.
Used ThreadingContext arg instead of NestedPools.
Use new PROFILER_ZONE3.

PiperOrigin-RevId: 793821255
 2025-08-11 15:34:52 -07:00
Ivo Ristovski List b56b2f05e4 Automated Code Change 
PiperOrigin-RevId: 789876258
 2025-08-01 13:29:50 -07:00
Jan Wassenberg 799c264df3 Pre-tune thread pool before matmul 
Also improve profiler annotations - remove near-zero ones and add more for startup

PiperOrigin-RevId: 789352414
 2025-07-31 08:45:26 -07:00
Jan Wassenberg d1638587f0 1.14x batch decode speedup: parallelize RMSNorm ops 
Activations was over-parallelized, use single pool instead.
Also improve profiler zone annotations,
pass through worker args (for tracking concurrency), now non-optional.

PiperOrigin-RevId: 788790976
 2025-07-30 00:55:45 -07:00
Jan Wassenberg e76e29ce11 De-singleton ThreadingContext so callers can pass in their own 
weights.cc: fix BindB argument for bf16 tensors
threading_test: enable autotune
PiperOrigin-RevId: 785763618
 2025-07-22 02:08:46 -07:00