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
0ae8646731
Fix remainder handling for Paligemma
...
No longer attempt to skip the remainder handling because B might also be a non-padded view.
PiperOrigin-RevId: 800890805
2025-08-29 07:25:52 -07:00
973e284ed6
Refactor Matmul to use a policy class for parallelization.
...
PiperOrigin-RevId: 800864489
2025-08-29 05:40:39 -07:00
6c39a2dea4
1.01x speedup: More bf16 activations to reduce DecompressA.
...
Also move observer call into function, format gemma_args.
PiperOrigin-RevId: 800827400
2025-08-29 03:19:01 -07:00
7288891439
Remove F64 partial storage in matmul.
...
Also remove no longer used kMaxN; row_ptrs only used for C
PiperOrigin-RevId: 800774757
2025-08-29 00:12:08 -07:00
98ddc166db
Expand ThreadingContext comments
...
PiperOrigin-RevId: 800479954
2025-08-28 08:32:10 -07:00
6128e758ff
Change ffw_out from B16 to F32.
...
PiperOrigin-RevId: 800330411
2025-08-28 00:01:39 -07:00
5411fd846d
Minor: batched NotifyGenerate, fix comment/dep
...
PiperOrigin-RevId: 799889802
2025-08-26 23:33:17 -07:00
86afd53076
1.04x speedup: Parallelize SoftCap
...
Also require opt-in constexpr flag for observer callbacks, update zones
PiperOrigin-RevId: 799655163
2025-08-26 11:55:20 -07:00
ed2f0bd1b0
Fix pos assertions, refs #665
...
Ensure the streaming func pos matches the number of calls.
Add two arguments that control pos+1 and pos+=1 behavior.
Also cleanup/add comments.
run: use batch_stream_func, add assert, higher verbosity for MM autotune output
PiperOrigin-RevId: 799511163
2025-08-26 04:50:40 -07:00
9bf0fe4e37
Internal change
...
PiperOrigin-RevId: 799509375
2025-08-26 04:44:08 -07:00
d3a5ddf657
Merge pull request #663 from junjihashimoto:feature/api-server
...
PiperOrigin-RevId: 797731089
2025-08-24 11:57:05 +02:00
73f1140dca
Fix an off-by-one error after StreamAndUpdateEOS() to remove the MSAN warning about reading an uninitialized variable in the kv_cache.
...
The logic for choosing whether or not to attend to the last token during prefill wasn't completely consistent with StreamAndUpdateEOS(), causing an off-by-one error that prevented the kv_cache from being fully populated.
PiperOrigin-RevId: 797614310
2025-08-20 22:59:58 -07:00
41321611fd
feature: add API server and client with Google protocol
2025-08-21 11:32:48 +09:00
78573b6718
Internal change. Add deduction for 270M.
...
PiperOrigin-RevId: 795041810
2025-08-14 08:04:38 -07:00
d044801c1d
Internal change
...
PiperOrigin-RevId: 794620076
2025-08-13 09:47:45 -07:00
71406cf6d0
More profiler interface fixes: hwy:: plus avoid ADD_ZONE
...
PiperOrigin-RevId: 794493165
2025-08-13 03:15:48 -07:00
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
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
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
4e062d68f7
Update BlobWriter comments, WriteAll->Finalize
...
PiperOrigin-RevId: 790792133
2025-08-04 10:01:38 -07:00
701841897b
Default to disabling per-socket parallelization
...
weights: default to Read for small-batch (only look at qbatch, not the larger prefill tbatch)
PiperOrigin-RevId: 790787643
2025-08-04 09:49:14 -07:00
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
50ee1a3e92
Write SBS progressively.
...
(1) Directly write to file in BlobWriter::Add and destruct the MatOwner to release the rams.
(2) Write a fake header to indicate this is V2, and write correct header and directory at the end of the file.
(3) Tested on loading sbs written the old way, and new way, both worked.
PiperOrigin-RevId: 789306837
2025-07-31 06:05:38 -07:00
8715eda512
Improved layer idx parsing
...
PiperOrigin-RevId: 788868522
2025-07-30 05:49:45 -07:00
d831ddce5b
Fix file mapping: was letting the smart pointer go out of scope
...
Also save+print the IO mode used.
PiperOrigin-RevId: 788848165
2025-07-30 04:30:10 -07:00
d22ba2ac96
Update layer index parsing and allow tokenizer override
...
PiperOrigin-RevId: 788797948
2025-07-30 01:22:34 -07:00
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
ac0d751d20
Rename GetModelConfig->Config
...
PiperOrigin-RevId: 788506480
2025-07-29 10:18:12 -07:00
33fabd4ed1
Internal change.
...
PiperOrigin-RevId: 788463042
2025-07-29 08:21:29 -07:00
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
5474146129
Back to f32 kv_cache, but via typedef
...
PiperOrigin-RevId: 785422614
2025-07-21 07:05:35 -07:00
56c9196eb6
Add blob_path to config deduction message
...
PiperOrigin-RevId: 782188689
2025-07-11 18:58:56 -07:00
4bc44d5678
Minor: ModelWeightsPtrs -> WeightsPtrs
...
PiperOrigin-RevId: 781954533
2025-07-11 06:11:51 -07:00
a04cc287b2
Move MatMulEnv out of Gemma to enable concurrent calls
...
Also update benchmark_helper config print: add profiler, remove free mem
PiperOrigin-RevId: 774662974
2025-06-23 01:20:09 -07:00
0f70f285e0
1.1x prefill and decode speedup (attention/activations)
...
Optimizations
- Better load-balancing in attention threading
(Previously, clusters were limited by #heads)
- Add MulByConstTo to avoid zero-init
- Parallel activations
Cleanup
- Prepare for RowPtr in A or B
- Pass through thread_id to ops
- Avoid warning in bench_matmul
PiperOrigin-RevId: 773723423
2025-06-20 08:59:53 -07:00
4f5785b0fd
Update instrumentation for new Highway wall-time profiler
...
Pass the thread index through and use new zone_id.
PiperOrigin-RevId: 773344242
2025-06-19 07:46:04 -07:00
7f62c2606e
Fix bf16 KV recompression and Rope(), fixes #608
...
Also add more helpful error message for prompt > seq_len
Also update ops_test, adding coverage for Rope().
PiperOrigin-RevId: 772945644
2025-06-18 09:14:20 -07:00
88284387db
Reduce warning noise.
...
PiperOrigin-RevId: 772941142
2025-06-18 09:01:40 -07:00
343482c7ef
1.02x batch decode speedup: BF16 KV cache
...
ops-inl.h: Vectorize Rope(), template
Remove unused MulBy, and extra-arg overloads of MulByConst and Softmax
Fix for DecompressAndZeroPad: ensure second vector filled
PiperOrigin-RevId: 772779163
2025-06-17 23:21:59 -07:00
f2adbfbcab
Batch inference fixes: set pos during prefill, fix assert
...
PiperOrigin-RevId: 772458760
2025-06-17 07:09:44 -07:00
cd80d8b24d
Speed up builds by skipping rarely used targets
...
Centralize previous code into GEMMA_DISABLED_TARGETS
PiperOrigin-RevId: 772433723
2025-06-17 05:44:20 -07:00
9a02d6be68
Add --prompt_file and testdata for it. Refs #608
...
Linux terminals truncate input after 4096 chars.
testdata is Frankenstein from project Gutenberg, which are long out of copyright.
Also fix loss of coherence after long context caused by incorrect IsGlobalLayer.
Move that to config.h and use max_seq_len as the initializer to make this clear.
Also avoid dynamic allocation for GriffinActivations.
PiperOrigin-RevId: 772333225
2025-06-16 23:41:07 -07:00
5f3797f6e1
Allow creating empty `AttentionActivations` for experimental code.
...
PiperOrigin-RevId: 772077675
2025-06-16 10:19:11 -07:00
6773e4517c
Split Activations into Griffin/Attention to reduce memory usage for attention-only tests.
...
PiperOrigin-RevId: 772025282
2025-06-16 07:52:59 -07:00
7aac765e96
Add `Append` method to `AllQueries`
2025-06-16 20:39:27 +08:00
e5c81f64a1
Major refactor: clarify query_idx (global) vs qi. Refs #607
...
Fix missing pos increment for last prefill and check that in gemma_test.
Thanks to @ufownl for pointing this out.
Change argument lists to QBatch with accessors.
Increase default seq_len to 8k.
PiperOrigin-RevId: 771937385
2025-06-16 02:42:02 -07:00
01cdefeda7
1.64x batch=1 prefill speedup: nested parallelization for Attention
...
(DotSoftmaxWeightedSum)
Also fix tsan error in matmul (atomic_flag instead of static)
PiperOrigin-RevId: 770241705
2025-06-11 11:28:46 -07:00
c027a45a2e
MatPtr-ify KV, shared div_seq_len, --seq_len flag
...
PiperOrigin-RevId: 770194455
2025-06-11 09:49:38 -07:00
b84149310b
Fix paligemma, update its test
...
Must not pass image tokens to the EmbedMMToken used for text.
Caught by next presubmit test.
paligemma_test: move function bodies into class, regroup variables
PiperOrigin-RevId: 770040014
2025-06-11 02:12:12 -07:00
Jan Wassenberg
Marie White
Rhett Stucki
Junji Hashimoto
Phil Culliton
The gemma.cpp Authors
Charles Zhao
Jeremiah Harmsen
Biruk Mammo
RangerUFO