Pascal 57b557cb95 models: pad on the left with ggml_pad_ext (#29567) ...

* models: pad on the left with ggml_pad_ext

The Parakeet, LFM2-Audio, Granite Speech and Gemma 4 audio encoders
build a left padding as a right pad followed by a roll, and DFlash2
concatenates a zero filled block in front of the previous tokens.
ggml_pad_ext does both in one node now that every backend supports a
left padding. The Gemma 4 audio embeddings are bit identical.

* models: skip the DFlash2 taps that only read padding

A tap at or past block_size shifts every row out of the block, so its
term is zero. The loop runs min(kernel_size, block_size) taps.

2026-09-28 20:56:15 +02:00

..

models

models: pad on the left with ggml_pad_ext (#29567)

2026-09-28 20:56:15 +02:00

CMakeLists.txt

cmake : remove precompiled headers (#28892)

2026-09-14 16:07:28 +02:00

llama-adapter.cpp

gguf : align the data section relative to the GGUF start, not the file (#28993)

2026-09-17 09:19:44 +02:00

llama-adapter.h

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

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

llama-arch.cpp

hrm : fix layer placement of z_l_init weight (#29512)

2026-09-27 10:16:23 +03:00

llama-arch.h

llama : add llama_prec_policy + model-driven W4A4 path (#24364)

2026-09-25 11:36:35 +03:00

llama-batch.cpp

llama: add llama_batch_ext (#24669)

2026-09-24 16:25:07 +02:00

llama-batch.h

llama: add llama_batch_ext (#24669)

2026-09-24 16:25:07 +02:00

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

context : do not re-reserve the scheduler when toggling causal_attn (#28751)

2026-09-28 11:58:51 +03:00

llama-context.h

server : allow RANK pooling batch splitting for causal LLM rerankers (ie. Qwen3 and Qwen3-VL) (#28876)

2026-09-27 23:28:10 +02:00

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

context : autoscale n_ctx_train when yarn scaling specified (#28030)

2026-09-01 19:59:54 +03:00

llama-ext.h

spec : add DFlash2 support (local convolution + candidate selector) (#27342) (#27816)

2026-08-27 19:17:07 +02:00

llama-grammar.cpp

llama-grammar: fix numeric truncation for token_id parsing (#29382)

2026-09-24 21:43:26 +03:00

llama-grammar.h

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

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

llama-graph.cpp

server : allow RANK pooling batch splitting for causal LLM rerankers (ie. Qwen3 and Qwen3-VL) (#28876)

2026-09-27 23:28:10 +02:00

llama-graph.h

llama : add llama_prec_policy + model-driven W4A4 path (#24364)

2026-09-25 11:36:35 +03:00

llama-hparams.cpp

llama: add llama_batch_ext (#24669)

2026-09-24 16:25:07 +02:00

llama-hparams.h

model : add support for HrmTextForCausalLM (DFM Mimir 1B) (#27625)

2026-09-16 15:18:45 +02:00

llama-impl.cpp

llama : fix K/V and recurrent state cleanup after failed restores (#27530)

2026-09-26 10:23:03 +03:00

llama-impl.h

llama : fix K/V and recurrent state cleanup after failed restores (#27530)

2026-09-26 10:23:03 +03:00

llama-io.cpp

server : avoid checkpoint data host copies (#22558)

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

llama-io.h

llama : fix K/V and recurrent state cleanup after failed restores (#27530)

2026-09-26 10:23:03 +03:00

llama-kv-cache-dsa-iswa.cpp

model: add dots3-note (#27060)

2026-08-21 19:52:34 +02:00

llama-kv-cache-dsa-iswa.h

model: add dots3-note (#27060)

2026-08-21 19:52:34 +02:00

llama-kv-cache-dsa.cpp

llama : fix K/V and recurrent state cleanup after failed restores (#27530)

2026-09-26 10:23:03 +03:00

llama-kv-cache-dsa.h

llama : allocate indexer cache only in "full" indexer layers (#26474)

2026-08-03 14:56:30 +02:00

llama-kv-cache-dsv4.cpp

Deepseek 4: -sm tensor (#26490)

2026-08-24 09:20:25 +03:00

llama-kv-cache-dsv4.h

DeepseekV4 MTP + DSpark (#25784)

2026-08-02 20:55:34 +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-msa.cpp

model: M3: Move MSA into a new memory implementation (#26338)

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

llama-kv-cache-msa.h

model: M3: Move MSA into a new memory implementation (#26338)

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

llama-kv-cache.cpp

llama : fix K/V and recurrent state cleanup after failed restores (#27530)

2026-09-26 10:23:03 +03:00

llama-kv-cache.h

llama : fix K/V and recurrent state cleanup after failed restores (#27530)

2026-09-26 10:23:03 +03:00

llama-kv-cells.h

kv-cells: look up the n-gram history in the sequence position index (#28040)

2026-09-01 20:16:07 +02:00

llama-memory-hybrid-idx.cpp

context : do not re-reserve the scheduler when toggling causal_attn (#28751)

2026-09-28 11:58:51 +03:00

llama-memory-hybrid-idx.h

context : do not re-reserve the scheduler when toggling causal_attn (#28751)

2026-09-28 11:58:51 +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 : fix K/V and recurrent state cleanup after failed restores (#27530)

2026-09-26 10:23:03 +03:00

llama-memory-hybrid.h

llama + spec: MTP Support (#22673)

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

llama-memory-recurrent.cpp

llama : fix K/V and recurrent state cleanup after failed restores (#27530)

2026-09-26 10:23:03 +03:00

llama-memory-recurrent.h

llama : fix K/V and recurrent state cleanup after failed restores (#27530)

2026-09-26 10:23:03 +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

llama : add missing headers (#28566)

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

llama-mmap.h

llama: model_loader: add TENSOR_READ_LAZY (#27794)

2026-08-27 15:14:34 +02:00

llama-model-loader.cpp

gguf : align the data section relative to the GGUF start, not the file (#28993)

2026-09-17 09:19:44 +02:00

llama-model-loader.h

llama: improve TENSOR_READ_LAZY handling (#27837)

2026-08-30 16:59:48 +02:00

llama-model-saver.cpp

llama : add llama_prec_policy + model-driven W4A4 path (#24364)

2026-09-25 11:36:35 +03:00

llama-model-saver.h

model: add Qwen3.8-Flash-Next (qwen4exp) (#27742)

2026-08-27 21:32:31 +02:00

llama-model.cpp

llama : add llama_prec_policy + model-driven W4A4 path (#24364)

2026-09-25 11:36:35 +03:00

llama-model.h

llama : add llama_prec_policy + model-driven W4A4 path (#24364)

2026-09-25 11:36:35 +03:00

llama-quant.cpp

quantize: row-slab stream to avoid thread starvation (#27830)

2026-09-01 11:18:54 +02:00

llama-quant.h

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

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

llama-sampler.cpp

sampler: reduce the size of the probe (#29285)

2026-09-23 08:12:04 +03:00

llama-sampler.h

llama : support multi-output backend sampling (#25532)

2026-08-10 16:58:56 +03:00

llama-version.h.in

llama: fix whole source code rebuilt on each new commit (#28278)

2026-09-03 23:53:04 +02:00

llama-vocab.cpp

test-llama-archs : generate dummy test vocab (#29084)

2026-09-19 11:27:46 +03:00

llama-vocab.h

vocab : add ufakzeka pre-tokenizer (#29033)

2026-09-18 11:45:11 +03:00

llama.cpp

tests : fix ggml init (#29554)

2026-09-28 10:24:21 +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 : include '~' in collapsed symbol class (#26972)

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

unicode.h

vocab: fix Gemma4 tokenizer (#21343)

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