3 people 1464c62d88 metal: implement DSv4 Lightning Indexer (#25893) ...

* metal: implement F16 Lightning Indexer

- Implement GGML_OP_LIGHTNING_INDEXER for 128-dimensional, 64-head inputs
  with F32 queries and weights plus F16 keys and masks.
- Add tiled and tail kernels and test KV lengths around 8- and 64-element
  boundaries.

llama-bench (--mmap 1, -fa 1, -p 512, -n 128; d=0/10k/20k/30k):

Before:
- pp512: 153.73 ± 0.87 t/s
- tg128: 8.91 ± 0.04 t/s
- pp512 @ d10000: 73.90 ± 0.39 t/s
- tg128 @ d10000: 8.66 ± 0.03 t/s
- pp512 @ d20000: 45.83 ± 0.18 t/s
- tg128 @ d20000: 8.26 ± 0.03 t/s
- pp512 @ d30000: 33.40 ± 0.21 t/s
- tg128 @ d30000: 7.94 ± 0.01 t/s

After:
- pp512: 155.19 ± 0.91 t/s
- tg128: 8.95 ± 0.04 t/s
- pp512 @ d10000: 86.95 ± 0.69 t/s
- tg128 @ d10000: 9.00 ± 0.05 t/s
- pp512 @ d20000: 62.01 ± 0.45 t/s
- tg128 @ d20000: 8.68 ± 0.04 t/s
- pp512 @ d30000: 49.18 ± 0.33 t/s
- tg128 @ d30000: 8.60 ± 0.02 t/s

Assisted-by: Codex

* metal: stage Lightning Indexer K tiles

- Stage and dequantize K in F16 threadgroup memory before simdgroup matrix loads.
- Zero-fill partial tiles and guard stores so all KV segments use the same numerical path.
- Support F32, F16, BF16, Q4_0, Q4_1, Q5_0, Q5_1, and Q8_0 K caches.

llama-bench (--mmap 1, -fa on, -p 512, -n 128; d=0/10k/20k):

- pp512: 160.38 +/- 1.01 t/s
- tg128: 9.08 +/- 0.03 t/s
- pp512 @ d10000: 88.37 +/- 0.46 t/s
- tg128 @ d10000: 9.07 +/- 0.04 t/s
- pp512 @ d20000: 62.53 +/- 0.46 t/s
- tg128 @ d20000: 8.84 +/- 0.03 t/s

Assisted-by: Codex

* dedup Lightning Indexer constants, fix flaky test

* cont : fix whitespace

---------

Co-authored-by: forforever73 <690105611@qq.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

2026-08-03 07:33:37 +03:00

..

peg-parser

common/peg : implement ac parser for stricter grammar generation (#24869)

2026-06-21 16:20:58 -05:00

snapshots

tests : avoid building get-model.cpp many times (#26317)

2026-07-30 19:34:04 +03:00

.gitignore

tests : add unit test coverage for llama_tensor_get_type (#20112)

2026-04-02 22:53:58 +02:00

CMakeLists.txt

tests : avoid building get-model.cpp many times (#26317)

2026-07-30 19:34:04 +03:00

gguf-model-data.cpp

ci : add [no release] keyword + fix sanitizer builds (#23728)

2026-05-26 19:05:48 +03:00

gguf-model-data.h

tests : add unit test coverage for llama_tensor_get_type (#20112)

2026-04-02 22:53:58 +02:00

test-alloc.cpp

tests: Harmonize header use (#25616)

2026-07-13 15:36:51 +03:00

test-arg-parser.cpp

args: add -lm mlock where it mlocks but doesnt mmap (#26135)

2026-07-27 16:44:08 +08:00

test-autorelease.cpp

tests : avoid building get-model.cpp many times (#26317)

2026-07-30 19:34:04 +03:00

test-backend-ops.cpp

metal: implement DSv4 Lightning Indexer (#25893)

2026-08-03 07:33:37 +03:00

test-backend-sampler.cpp

tests : avoid building get-model.cpp many times (#26317)

2026-07-30 19:34:04 +03:00

test-barrier.cpp

Fix race conditions in threadpool when dealing with dynamic/frequent n_threads changes (#17748)

2025-12-10 12:32:23 -08:00

test-batch-alloc.cpp

llama-batch: add unit test (#25471)

2026-07-10 11:04:31 +08:00

test-c.c

ggml : remove kompute backend (#14501)

2025-07-03 07:48:32 +03:00

test-chat-auto-parser.cpp

Add support for Laguna XS.2 & M.1 (#25165)

2026-07-22 09:54:08 +08:00

test-chat-peg-parser.cpp

chat : add qwen3 specialized parser (#26252)

2026-08-02 04:13:20 -05:00

test-chat-template.cpp

jinja: add --dump-prog for debugging (#25086)

2026-06-28 15:50:31 +02:00

test-chat.cpp

chat : add qwen3 specialized parser (#26252)

2026-08-02 04:13:20 -05:00

test-col2im-1d.cpp

ggml : add GGML_OP_COL2IM_1D (#24206)

2026-06-09 12:01:37 +03:00

test-double-float.cpp

ggml : minor naming changes (#8433)

2024-07-12 10:46:02 +03:00

test-export-graph-ops.cpp

tests: export-graph-ops: exit gracefully when called w/o arguments (#25619)

2026-07-14 13:15:41 +03:00

test-gbnf-validator.cpp

cmake : do not include ./src as public for libllama (#13062)

2025-04-24 16:00:10 +03:00

test-gguf-model-data.cpp

tests : add unit test coverage for llama_tensor_get_type (#20112)

2026-04-02 22:53:58 +02:00

test-gguf.cpp

gguf : add tensor shape accessor (#24405)

2026-07-13 13:55:15 +03:00

test-grammar-integration.cpp

common/grammar: fix grammar parsing issues to prevent stack overflow and hangs (#18604)

2026-03-21 18:43:35 +01:00

test-grammar-llguidance.cpp

tool/ex/tests: consistently free ctx, then model (#18168)

2025-12-22 11:00:37 +01:00

test-grammar-parser.cpp

common/grammar: fix grammar parsing issues to prevent stack overflow and hangs (#18604)

2026-03-21 18:43:35 +01:00

test-jinja.cpp

common: add subproc.h wrapper, disabled on android/ios (#26102)

2026-07-26 20:54:25 +02:00

test-json-schema-to-grammar.cpp

common/json-schema-to-grammar : align spacing rules with parsers (#24835)

2026-06-20 17:43:04 -05:00

test-llama-archs.cpp

test: fix some CI errors (#26415)

2026-08-02 00:16:29 +02:00

test-llama-grammar.cpp

common/grammar: fix grammar parsing issues to prevent stack overflow and hangs (#18604)

2026-03-21 18:43:35 +01:00

test-log.cpp

common: Intentionally leak logger instance to fix hanging on Windows (#22273)

2026-04-29 10:58:43 +03:00

test-lora-conversion-inference.sh

cli: new CLI experience (#17824)

2025-12-10 15:28:59 +01:00

test-model-load-cancel.cpp

tests : avoid building get-model.cpp many times (#26317)

2026-07-30 19:34:04 +03:00

test-mtmd-c-api.c

mtmd : add video input support (#24269)

2026-06-08 14:40:12 +03:00

test-opt.cpp

tests : fix test-opt with GGML_BACKEND_DL (#15599)

2025-08-26 22:14:38 +02:00

test-peg-parser.cpp

Autoparser - complete refactoring of parser architecture (#18675)

2026-03-06 21:01:00 +01:00

test-quant-type-selection.cpp

tests : avoid building get-model.cpp many times (#26317)

2026-07-30 19:34:04 +03:00

test-quantize-fns.cpp

Add Q2_0 quantization: type definition and CPU backend (#24448)

2026-07-07 12:05:47 -07:00

test-quantize-perf.cpp

ci: run the x64 and arm ci on the github machines instead (#16183)

2025-09-25 08:06:06 +03:00

test-quantize-stats.cpp

args: refactor mlock/mmap/directio into load-mode (#20834)

2026-07-23 20:32:56 +08:00

test-reasoning-budget.cpp

common : add support for multiple end sequences in the reasoning budget sampler (#25544)

2026-07-25 11:58:09 +02:00

test-recurrent-state-rollback.cpp

DeepseekV4 MTP + DSpark (#25784)

2026-08-02 20:55:34 +08:00

test-rope.cpp

ggml-cpu: templateify ggml_compute_forward_rope_f32 and _f16 (#16805)

2025-11-11 13:33:24 +02:00

test-rset-release.cpp

tests : avoid building get-model.cpp many times (#26317)

2026-07-30 19:34:04 +03:00

test-sampling.cpp

sampling : remove unconditional softmax+sort in top-n-sigma sampler (#22645)

2026-06-22 14:08:32 +03:00

test-save-load-state.cpp

tests : remove unnecessary sync in test-save-load-state (#26166)

2026-07-27 13:11:20 +03:00

test-state-restore-fragmented.cpp

common : only load backends when required (#22290)

2026-05-05 09:23:50 +02:00

test-thread-safety.cpp

tests : synchronize contexts at end of test-thread-safety (#24935)

2026-06-25 09:22:51 +03:00

test-tokenizer-0.cpp

tool/ex/tests: consistently free ctx, then model (#18168)

2025-12-22 11:00:37 +01:00

test-tokenizer-0.py

requirements : update transformers to 5.5.1 (#21617)

2026-04-09 12:36:29 +02:00

test-tokenizer-0.sh

model : add Jina Embeddings v5 Nano (partial EuroBERT) support (#19826)

2026-02-26 12:14:09 +01:00

test-tokenizer-1-bpe.cpp

tool/ex/tests: consistently free ctx, then model (#18168)

2025-12-22 11:00:37 +01:00

test-tokenizer-1-spm.cpp

tool/ex/tests: consistently free ctx, then model (#18168)

2025-12-22 11:00:37 +01:00

test-tokenizer-random.py

requirements : update transformers to 5.5.1 (#21617)

2026-04-09 12:36:29 +02:00

test-tokenizers-repo.sh

devops: add s390x & ppc64le CI (#15925)

2025-09-27 02:03:33 +08:00

testing.h

common : implement new jinja template engine (#18462)

2026-01-16 11:22:06 +01:00