Commit Graph

13 Commits

Author SHA1 Message Date
Jan Wassenberg 8532da47f7 Major refactor of allocator/args:
use new ThreadingContext2 instead of monostate/init in each frontend
Add ThreadingArgs(replaces AppArgs)

backprop: use Packed() accessor and MakePacked factory and row-based access to allow for stride
compress_weights: remove, moving to py-only exporter instead

Move MatPtr to mat.h and revise interface:
- Generic MatOwner
- rename accessors to Packed*
- support stride/row accessors, fix RowPtr stride

Add TypeBits(Type)
Move GenerateMat to test_util-inl for sharing between matmul test/bench
Move internal init to gemma.cc to avoid duplication
Rename GemmaEnv model_ to gemma_ for disambiguating vs upcoming ModelStorage
Remove --compressed_weights, use --weights instead.
tensor_index: add ExtentsFromInfo and TensorIndexLLM/Img
Allocator: use normal unique_ptr for AllocBytes so users can call directly
threading: use -> because AlignedPtr no longer assumes arrays
PiperOrigin-RevId: 745918637
2025-04-10 01:29:54 -07:00
Copybara-Service bef91a3f03 Merge pull request #529 from ufownl:refactor/wrap_and_tokenize
PiperOrigin-RevId: 745174371
2025-04-08 09:22:26 -07:00
RangerUFO ca4ee2b63f Refactor `WrapAndTokenize` to work properly with Gemma3 2025-03-29 11:31:39 +08:00
Jan Wassenberg 1b72c22345 Refactor Gemma ctor and improve pool NUMA support
Gemma receives a MatMulEnv arg, with comment on lifetime
Split threading into topology so the latter can be used in allocator
Add AllocClasses() for non-POD (ThreadPool)
Support binding pool to NUMA node
Update threading_test with latency measurements
Also update Highway version.

PiperOrigin-RevId: 736904748
2025-03-14 10:19:00 -07:00
Daniel Keysers 493688f6f1 Allow interactive use with new single-file weight format.
Add section about new weights format to README.md.
Remove model_type_required parameter.
Update error handling for flags.

PiperOrigin-RevId: 715788822
2025-01-15 07:22:33 -08:00
Ray Smith 9d40f0117e Added ability to load/save a complete model file, including tokenizer.
PiperOrigin-RevId: 707914366
2024-12-19 07:59:41 -08:00
Jan Wassenberg 02ce1e344f Use NestedPools, add NUMA infra
Improved threading.h, fix thread counts for single package/cluster systems
Temporarily forces to a single socket. Prefill 29.28 tps, decode 6.92.

Also fix benchmarks.cc build, update tensor allocator to Allocator

PiperOrigin-RevId: 687307167
2024-10-18 08:11:18 -07:00
Daniel Keysers a4d6adbc43 Introduce QueryResult in GemmaEnv and add a shortcut for WrapAndTokenize.
Remove max_tokens (and rely on only max_generated_tokens).

PiperOrigin-RevId: 685662260
2024-10-14 04:45:21 -07:00
Daniel Keysers a8e08778d4 Add an additional QueryModel() overload to GemmaEnv.
Use args only in GemmaEnv constructor, store everything else in RuntimeConfig.
Add runtime option to turn off thread spinning.

PiperOrigin-RevId: 670467320
2024-09-03 02:25:19 -07:00
Jan Wassenberg 22995c699d Simplify pos handling, auto-increment output arg
- no longer multiply by num_queries
- remove unused interleaved prompts
- Rename to Queries*
- Rename batch_start/interleaved_pos/pos to queries_pos

PiperOrigin-RevId: 663331823
2024-08-15 09:25:26 -07:00
Jan Wassenberg 5e433e774a 1.1x prefill speedup, revamp threading in preparation for hierarchical parallelism.
Limit thread counts to detected. Add max_clusters arg.
Update detection logic to check for smt0 - previously we pinned to some siblings.

PiperOrigin-RevId: 659755311
2024-08-05 18:50:09 -07:00
Jan Wassenberg aaf51898b6 Major revamp #2 of Prefill: fix token order, parallel for multi-query
- Allocate only the required KV caches and activation batch size
- Add flags for batch sizes
- Const-correct interface: Span of const int.
- Also clean up the KVCache arg to a span.
- Move kPrefillBatchSize into RuntimeConfig and remove related global constants.

PiperOrigin-RevId: 655893197
2024-07-25 03:28:55 -07:00
Jan Wassenberg cbb67b4ee0 Move benchmark_helper to evals/, weights_raw to compression/.
PiperOrigin-RevId: 650155983
2024-07-08 01:13:23 -07:00
Renamed from gemma/benchmark_helper.h (Browse further)