François-Xavier Gsell b3daa077a5 vulkan: sparse flash attention for quantized K/V (#29639) ...

* vulkan: sparse flash attention for quantized K/V

Assisted-by: Claude

* vulkan: single-scan sparse FA index compaction

The compaction ran one workgroup per mask row and walked the row in
BLOCK_SIZE chunks, with a workgroup scan per chunk. For decode that is
one workgroup doing KV/1024 barrier-bound iterations, so at 128k cells
it cost more than the sparse attention it feeds.

Split the row into contiguous segments instead: one per subgroup with
ballot counting over coalesced loads, or one per thread without
subgroups. A single scan over the segment counts then gives each
segment its output offset. The index list stays ascending.

2026-10-05 10:37:54 +02:00

..

fusion

ci: fix Fusion / metal by updating the qwen4exp baseline (#29812)

2026-10-01 19:57:34 +03:00

peg-parser

common/peg : handle invalid utf-8 sequences in the AST (#29161)

2026-09-20 06:51:40 -05:00

snapshots

tests : fix typo in test-quant-type-selection for nemotron 3 nano (#28835)

2026-09-13 18:50:46 +02:00

.gitignore

metal : single-source fusion table + fusion debug rework (#28164)

2026-09-11 12:41:54 +03:00

CMakeLists.txt

llama : fix unexpected graph reallocation in the k-pool models (#29958)

2026-10-05 11:36:25 +03:00

gguf-model-data.cpp

common : use fs::path for cache dirs (#29595)

2026-09-29 07:24:03 +02:00

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

ggml : add alloc_buffer_n to buffer type interface (#23671)

2026-10-02 11:08:08 +03:00

test-arg-parser.cpp

spec: Add benchmark-only synthetic speculative acceptance options (#27711)

2026-08-27 13:53:42 +03:00

test-autorelease.cpp

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

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

test-backend-ops.cpp

vulkan: sparse flash attention for quantized K/V (#29639)

2026-10-05 10:37:54 +02:00

test-backend-sampler.cpp

batch: migrate the rest of examples to llama_batch_ext (#29601)

2026-09-30 18:08:43 +02:00

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: support both embd + raw tokens in batch (#29622)

2026-10-05 01:35:49 +02:00

test-c.c

ggml : remove kompute backend (#14501)

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

test-chat-analysis.cpp

test: move tools/parser to tests (#27548)

2026-08-23 18:38:51 +02:00

test-chat-auto-parser.cpp

test: move tools/parser to tests (#27548)

2026-08-23 18:38:51 +02:00

test-chat-peg-parser.cpp

common/peg : handle invalid utf-8 sequences in the AST (#29161)

2026-09-20 06:51:40 -05:00

test-chat-template.cpp

test: move tools/parser to tests (#27548)

2026-08-23 18:38:51 +02:00

test-chat.cpp

chat : honor json_schema in Ling 3.0 parser (#29813)

2026-10-03 15:40:50 +02:00

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-fusion.cpp

batch: migrate the rest of examples to llama_batch_ext (#29601)

2026-09-30 18:08:43 +02:00

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 : reject tensor size that wraps after padding (#26979)

2026-09-29 22:46:20 +02:00

test-grammar-integration.cpp

common : implement common_schema internal representation for JSON schemas (#28736)

2026-09-12 16:14:50 -05:00

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

grammar : degrade max repetition >= 2000 to unbounded (#26613)

2026-08-05 07:39:10 -05:00

test-jinja.cpp

jinja : support coerced array attributes (#29574)

2026-09-30 15:33:26 +02:00

test-json-schema-to-grammar.cpp

json-schema : accept escaped hyphen in regex patterns (#29127)

2026-09-19 14:11:13 +02:00

test-json-schema.cpp

common : implement common_schema internal representation for JSON schemas (#28736)

2026-09-12 16:14:50 -05:00

test-llama-archs.cpp

llama: support both embd + raw tokens in batch (#29622)

2026-10-05 01:35:49 +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-metal-graph-optimize.cpp

metal : few-row MMA mat-mul (#29869)

2026-10-05 08:29:13 +03:00

test-model-load-cancel.cpp

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

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

test-model-resolution.cpp

args: fix cli download mmproj arg (#28977)

2026-09-30 20:45:39 +02:00

test-mtmd-c-api.c

mtmd: add mtmd_tokenize_from_parts() (#28250)

2026-09-02 21:20:10 +02:00

test-mtmd-impl.cpp

mtmd: fix mel preprocessor in LFM2 audio (#29403)

2026-09-25 18:52:44 +02:00

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 : fix typo in test-quant-type-selection for nemotron 3 nano (#28835)

2026-09-13 18:50:46 +02:00

test-quantize-fns.cpp

ggml-quants : avoid invalid rounding in qkx3 scale search (#29817)

2026-10-02 17:37:35 +03:00

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

cmake : introduce semantic versioning (#26839)

2026-08-12 14:15:03 +02:00

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

llama : fix unexpected graph reallocation in the k-pool models (#29958)

2026-10-05 11:36:25 +03:00

test-rope.cpp

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

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

test-rpc-multi-server.cpp

rpc: include nb in the get_alloc_size cache key and floor the result at ggml_nbytes (#29283)

2026-09-25 10:35:09 +03:00

test-rpc-multi-server.sh

rpc: avoid serializing buffers from other servers (#26500)

2026-08-30 20:26:16 +03:00

test-rset-release.cpp

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

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

test-sampling.cpp

llama : add missing headers (#28566)

2026-09-08 12:59:53 +02:00

test-save-load-state.cpp

llama : fix unexpected graph reallocation in the k-pool models (#29958)

2026-10-05 11:36:25 +03:00

test-state-restore-fragmented.cpp

llama : fix unexpected graph reallocation in the k-pool models (#29958)

2026-10-05 11:36:25 +03:00

test-thread-safety.cpp

batch: migrate the rest of examples to llama_batch_ext (#29601)

2026-09-30 18:08:43 +02:00

test-tiled-mulmat.cpp

ggml-cpu: tiled mul_mat for k-quants (#27851)

2026-09-26 08:38:57 +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

test-unicode.cpp

unicode : include '~' in collapsed symbol class (#26972)

2026-08-18 15:15:22 +02:00

testing.h

chat: refactor handling supports_string_content / supports_typed_content (#27130)

2026-08-16 12:45:33 +02:00