fairydreaming 2ed3c1abbb llama : make all KQ masks f16 if FA is used, remove zero attention bias, remove raw_k repeats in DeepSeek V4 (#25370) ...

* llama : make all KQ masks (except the lightning indexer one) f16 if FA is used and remove zero attention bias in DeepSeek V4

* llama : remove dead code that repeats unified raw_k cache for each stream in DeepSeek V4 - no longer needed as raw_k is always non-unified.

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>

2026-07-10 09:06:58 +02:00

..

models

llama : make all KQ masks f16 if FA is used, remove zero attention bias, remove raw_k repeats in DeepSeek V4 (#25370)

2026-07-10 09:06:58 +02:00

CMakeLists.txt

DeepSeek V4 (#24162)

2026-06-29 16:58:51 +08:00

llama-adapter.cpp

hparams : refactor hparams.n_layer (#24060)

2026-06-05 11:09:36 +03:00

llama-adapter.h

llama : re-enable manual LoRA adapter free (#19983)

2026-03-18 12:03:26 +02:00

llama-arch.cpp

DeepSeek V4 (#24162)

2026-06-29 16:58:51 +08:00

llama-arch.h

DeepSeek V4 (#24162)

2026-06-29 16:58:51 +08:00

llama-batch.cpp

llama-batch: fix allowed decreasing pos in a seq (#25449)

2026-07-08 19:24:34 +03:00

llama-batch.h

llama-batch: add n_keep_tail in split_equal for recurrent models (#25278)

2026-07-08 15:55:19 +08:00

llama-chat.cpp

chat : add Granite 4.1 chat template (#23518)

2026-05-28 13:13:33 +02:00

llama-chat.h

chat : add Granite 4.1 chat template (#23518)

2026-05-28 13:13:33 +02:00

llama-context.cpp

llama: refactor fused ops (#24646)

2026-07-08 18:18:09 +08:00

llama-context.h

llama: refactor fused ops (#24646)

2026-07-08 18:18:09 +08:00

llama-cparams.cpp

cparams : rename LLAMA_MAX_PARALLEL_SEQUENCES to LLAMA_MAX_SEQ (#14188)

2025-06-15 10:08:58 +03:00

llama-cparams.h

spec : Support Step3.5/3.7 flash mtp3 (#24340)

2026-06-21 11:33:18 +03:00

llama-ext.h

spec : Support Step3.5/3.7 flash mtp3 (#24340)

2026-06-21 11:33:18 +03:00

llama-grammar.cpp

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

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

llama-grammar.h

common/grammar : replace problematic backtracking regex [\s\S]* (#18342)

2026-01-03 16:02:43 -06:00

llama-graph.cpp

llama : make all KQ masks f16 if FA is used, remove zero attention bias, remove raw_k repeats in DeepSeek V4 (#25370)

2026-07-10 09:06:58 +02:00

llama-graph.h

llama: refactor fused ops (#24646)

2026-07-08 18:18:09 +08:00

llama-hparams.cpp

spec: fix segfault error on long prompts for eagle3 (#24707)

2026-06-17 17:29:49 +03:00

llama-hparams.h

DeepSeek V4 (#24162)

2026-06-29 16:58:51 +08:00

llama-impl.cpp

llama : correct platform-independent loading of BOOL metadata (#21428)

2026-04-06 01:40:38 +02:00

llama-impl.h

llama: refactor fused ops (#24646)

2026-07-08 18:18:09 +08:00

llama-io.cpp

server : avoid checkpoint data host copies (#22558)

2026-05-02 18:03:25 +03:00

llama-io.h

llama : add option to save memory in device buffers (#22679)

2026-05-05 06:35:07 +03:00

llama-kv-cache-dsa.cpp

llama-batch: add n_keep_tail in split_equal for recurrent models (#25278)

2026-07-08 15:55:19 +08:00

llama-kv-cache-dsa.h

model : support for DeepseekV32ForCausalLM with generic DeepSeek Sparse Attention (DSA) implementation (#23346)

2026-05-29 10:15:17 +02:00

llama-kv-cache-dsv4.cpp

llama-batch: add n_keep_tail in split_equal for recurrent models (#25278)

2026-07-08 15:55:19 +08:00

llama-kv-cache-dsv4.h

DeepSeek V4 (#24162)

2026-06-29 16:58:51 +08:00

llama-kv-cache-iswa.cpp

llama-batch: add n_keep_tail in split_equal for recurrent models (#25278)

2026-07-08 15:55:19 +08:00

llama-kv-cache-iswa.h

DeepSeek V4 (#24162)

2026-06-29 16:58:51 +08:00

llama-kv-cache.cpp

llama-batch: add n_keep_tail in split_equal for recurrent models (#25278)

2026-07-08 15:55:19 +08:00

llama-kv-cache.h

DeepSeek V4 (#24162)

2026-06-29 16:58:51 +08:00

llama-kv-cells.h

kv-cache : avoid kv cells copies (#24277)

2026-06-07 21:42:54 +03:00

llama-memory-hybrid-iswa.cpp

llama-batch: add n_keep_tail in split_equal for recurrent models (#25278)

2026-07-08 15:55:19 +08:00

llama-memory-hybrid-iswa.h

llama + spec: MTP Support (#22673)

2026-05-16 20:06:23 +08:00

llama-memory-hybrid.cpp

llama-batch: add n_keep_tail in split_equal for recurrent models (#25278)

2026-07-08 15:55:19 +08:00

llama-memory-hybrid.h

llama + spec: MTP Support (#22673)

2026-05-16 20:06:23 +08:00

llama-memory-recurrent.cpp

llama-batch: add n_keep_tail in split_equal for recurrent models (#25278)

2026-07-08 15:55:19 +08:00

llama-memory-recurrent.h

llama : MTP clean-up (#23269)

2026-05-19 15:32:58 +03:00

llama-memory.cpp

memory : correctly handle failure in apply() (#14438)

2025-06-30 18:03:03 +03:00

llama-memory.h

llama : add Gemma4 MTP (#23398)

2026-06-07 20:50:54 +08:00

llama-mmap.cpp

Update llama-mmap to use ftello/fseeko (#22497)

2026-04-30 14:17:52 -07:00

llama-mmap.h

llama: fix llama-model-saver (#20503)

2026-03-25 12:53:16 +02:00

llama-model-loader.cpp

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

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

llama-model-loader.h

llama + spec: MTP Support (#22673)

2026-05-16 20:06:23 +08:00

llama-model-saver.cpp

Add arch support for cohere2-MoE (#24260)

2026-06-13 19:49:00 +02:00

llama-model-saver.h

llama: fix llama-model-saver (#20503)

2026-03-25 12:53:16 +02:00

llama-model.cpp

CUDA: remove -sm row, refactor cuBLAS (#24216)

2026-07-06 20:04:53 +02:00

llama-model.h

llama : add llama_model_ftype_name() (#25134)

2026-07-02 17:26:47 +02:00

llama-quant.cpp

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

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

llama-quant.h

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-sampler.cpp

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

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

llama-sampler.h

llama : rename llama-sampling to llama-sampler (#19363)

2026-02-06 07:26:54 +01:00

llama-vocab.cpp

fix: OOB reads in UGM tokenizer (precompiled_charsmap handling) (#18750)

2026-07-08 08:02:09 +03:00

llama-vocab.h

vocab : refactor normalizer flags into options struct, add strip_accents (#24371)

2026-06-11 10:36:50 +03:00

llama.cpp

llama : skip main_gpu validation when no devices are available (#23405)

2026-06-17 17:30:26 +03:00

unicode-data.cpp

server : better security control for public deployments (#9776)

2024-10-08 13:27:04 +02:00

unicode-data.h

llama : reduce compile time and binary size (#9712)

2024-10-02 15:49:55 +02:00

unicode.cpp

unicode,test: add Qwen3.5 non-backtracking tokenizer handler and regr… (#22110)

2026-05-14 11:03:40 +02:00

unicode.h

vocab: fix Gemma4 tokenizer (#21343)

2026-04-03 10:33:03 +02:00