Commit Graph
1445 Commits
Author SHA1 Message Date
Aldehir Rojas 4ddf2b9470 chat : implement inkling parser (#32381) 2026-11-16 19:48:24 +01:00
Niklas Wenzel 62a6d3a302 llama : migrate to llama_batch_ext (#32356)
* llama : migrate to llama_batch_ext

* mtmd : migrate zonos3-mini code

Added in https://github.com/ggml-org/llama.cpp/pull/32020
2026-11-16 15:16:12 +01:00
Titaniumtown 21fa9c043f kv-cells: avoid an O(n_cells) scan per sequence removal (#32380) 2026-11-16 10:52:09 +01:00
Seungjun Bae 18b74fa41d model : read qwen3vl output head size from the tensor (#32349)
Allows Qwen3-ForcedAligner, whose output head (5000 timestamp classes) is smaller than the vocab.
2026-11-15 19:45:17 +01:00
Xuan-Son Nguyen 7ae3c6b231 mtmd: add zonos3-mini TTS model (#32020)
* zonos3 init

* add audio gen pipeline

* fix string_format

* add default voice as gguf metadata

* better ref

* support voice clone

* add delivery params

* optimize speed

* nits

* nits 2

* add text normalization

* nits
2026-11-15 19:44:44 +01:00
Xuan-Son Nguyen a68799c609 model: support MiniMax-M3.1 (#32301) 2026-11-15 17:39:59 +01:00
Anton SokolchenkoandJames Pickering de32b268c4 Support DFLASH2 for Recursive Ripple-65B-Preview (#31904)
* fixed support for DFlash2 for Ripple 65B

* spec: Add NoPE handling to DFlash

(cherry picked from commit 89ea8e3e77e3359d17902a2db136022d5d419d88)

* spec: Fix NoPE not being picked up by DFlash

(cherry picked from commit 43393b95fda2ce7e7d243e2650bf7b1cadf1c732)

---------

Co-authored-by: James Pickering <james_pic@hotmail.com>
2026-11-15 19:36:08 +08:00
Tarek Dakhran e574a17b06 model : metal : workaround fusion for LFM3 (#32296)
* lfm3 : put the normed tensor first in residual adds to enable norm fusion

Assisted-by: Claude Opus 5.5

* tests : update Metal fusion baseline for lfm3

Assisted-by: Claude Opus 5.5
2026-11-15 01:05:20 +01:00
Piotr Wilkin (ilintar)andXuan Son Nguyen 5c008e0008 feat: add Inkling 2 support (text + vision) (#32217)
* convert : add Inkling2 text GGUF conversion

Assisted-by: Codex

* llama : implement Inkling2 text inference

Assisted-by: Codex

* tests : cover Inkling2 text support

Assisted-by: Codex

* conversion : dequantize packed Inkling2 experts in row chunks

Decode per-layer NVFP4 and MXFP8 schemes, validate companions, and use stored scale shapes with a warning for the declared MXFP8 [32,32] grid. Reorder packed w13 rows and their scale rows together. Keep normal GGUF outtype selection and 3D expert tensors.

Stream 128 rows per expert through LazyChunkedTensor. Real w13 (384x4608x4608) needs a 2.25 MiB F32 chunk instead of a 30.375 GiB expanded layer. Real-shaped sparse probes peak below 5.8 MiB of Python/NumPy chunk allocations, plus 5.2 MiB of callback metadata: budget about 16 MiB per projection including mapped pages, excluding runtime, other tensors and OS cache. Full-model chunk metadata is roughly 370 MiB.

Packed synthetic GGUF weights match the independent pinned vLLM decode bit-for-bit. CPU prefill/decode logits remain within 3.1e-6 absolute error, with 100% argmax agreement. Float fixtures, original-name conversion and CPU architecture checks pass. Real checkpoint conversion remains untested.

Assisted-by: Codex

* convert : add Inkling2 vision mmproj support

Assisted-by: Codex

* mtmd : implement Inkling2 still-image encoder

Assisted-by: Codex

* inkling2 : scope image loading

Assisted-by: Codex

* inkling2 : enable flash attention with folded bias and sinks

Assisted-by: Codex

* cuda : route per-head flash attention masks through vec

Assisted-by: Codex

* mtmd : support Inkling2 temporal frame means

Assisted-by: Codex

* style : restore shared image comment

Assisted-by: Codex

* tests : enlarge Inkling2 context fixture

Assisted-by: Codex

* inkling2 : load per-layer expert feed-forward widths

Assisted-by: Codex

* tests : add Inkling2 Metal fusion baselines

Assisted-by: Codex

* inkling2 : group and align registry entries

Assisted-by: Fable

* convert : regenerate the Inkling2 tokenizer hash with the update script

Assisted-by: Fable

* conversion : revert the print_registered_models change

Assisted-by: Fable

* conversion : sort the Inkling2 model map entries

Assisted-by: Fable

* convert : map Inkling2 vision checkpoint names in the tensor table

Assisted-by: Fable

* convert : map Inkling2 text checkpoint names in the tensor table

Assisted-by: Fable

* tests : document the Inkling2 packed expert conversion test

Assisted-by: Fable

* tests : cover Inkling2 checkpoint and transformers tensor names

Assisted-by: Fable

* llama : place Inkling2 fields and list entries by file convention

Assisted-by: Fable

* gguf-py : align Inkling2 tensor mapping comments

Assisted-by: Fable

* mtmd : place Inkling2 entries by file convention

Assisted-by: Fable

* tests : place Inkling2 cases after the existing ones

Assisted-by: Fable

* cuda : index per-head flash attention masks in the tile and mma kernels

Assisted-by: Claude
Claude-Session: https://claude.ai/code/session_01GbYSza1yxgmTz8wdr6uV8Q

* inkling2 : project the relative bias before the gather, drop arch branches

Assisted-by: Claude
Claude-Session: https://claude.ai/code/session_01GbYSza1yxgmTz8wdr6uV8Q

* convert : require Inkling2 hparams, add inkling2 pre-tokenizer

Assisted-by: Claude
Claude-Session: https://claude.ai/code/session_01GbYSza1yxgmTz8wdr6uV8Q

* mtmd : cap Inkling2 image size, drop video frame averaging

Assisted-by: Claude
Claude-Session: https://claude.ai/code/session_01GbYSza1yxgmTz8wdr6uV8Q

* inkling2 : fix CI build, Meta device assert and Windows conversion test

Assisted-by: Claude

* tests : use the default sliding window for the Inkling2 test model

Assisted-by: Claude

* simplify mtmd part

* give _v arch for vision

* remove alpha channel handling, it should be a follow up

* explicit rule about audio + vision models

* add audio support

* rm audio

* rm gguf mtmd rope base

* address review comment

* nits

* do not normalize embd from mtmd

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2026-11-15 00:51:31 +01:00
Niklas Wenzel f8cc5774e7 memory : fix non-consecutive position warning for M-RoPE (#32287) 2026-11-14 23:57:23 +01:00
Yuri Khrustalev 3e41ae69db llama : allocate the tensor staging buffer from the CPU buffer type (#31438)
* llama : allocate the tensor staging buffer from the CPU buffer type

* llama : drop the staging buffer test, reword the comment
2026-11-14 23:37:46 +01:00
miyan a956a852c9 Fix ctz64 on 32bit (#32273) 2026-11-14 19:06:52 +01:00
Aman Gupta d0764c5ee2 qwen2vl : apply FFN weight scales (#32241)
The qwen2vl graph passed NULL for the ffn_up/gate/down scales, so the
per-tensor NVFP4 scales loaded by the generic pass were never applied
and the model produced garbage (PPL ~1e6 on CUDA, NaN on CPU).

Pass the scales to build_ffn like qwen2 does.

Fixes #32101
2026-11-15 02:02:15 +08:00
Aman Gupta c56be864f4 ggml-backend : start a new split at an incompatible weight in a split without inputs (#31775) 2026-11-14 22:14:48 +08:00
Ruixiang Wang 32bdc3a89e spec + model: refactor DFlash based speculative decoding methods (#32016)
* dflash : move the DSpark markov head and backbone graphs to dspark.cpp

Move-only: build_dspark_markov_head, graph_dsv4, graph_dsv41 and
graph_mistral_large4 move verbatim. build_inp_target_features and
build_dspark_markov_head become static members of llama_model_dflash so
both files can use them.

* dflash : detect the head and the backbone once, split the loaders per file

load_arch_hparams sets llama_model_dflash::variant (DFlash, DFlash2,
DSpark, LiliCorr) and ::backbone (base, DSV4, DSV4.1, Mistral Large 4).
The head, backbone and base layer loaders become member helpers in
dflash.cpp, dflash2.cpp, lilicorr.cpp and dspark.cpp. build_arch_graph
dispatches on the backbone.

The DFlash2 and LiliCorr loaders create the DFlash2 conv tensors through
a helper in dflash2.cpp, right after their head tensors instead of in
the base layer loop; the other tensors keep their creation order. The
DFlash2 loader drops its copy of the conv group size check, which master
never reached.

* dflash : share the injection input, token embeddings and lm head lookups

build_inject_inp (target features + fc + encoder norm), get_tok_embd and
get_lm_head replace the copies in the base, DSV4, DSV4.1 and Mistral
Large 4 graphs. build_inp_target_features is file-static again.

* dflash : split the DFlash decoder into a graph per head

graph_base creates the shared inputs and provides build_inject,
build_inp_tokens, build_layers and build_logits. graph_dflash
(dflash.cpp), graph_dflash2 (dflash2.cpp), graph_dspark (dspark.cpp) and
graph_lilicorr (lilicorr.cpp) assemble them and add their head; the
selector, scorer and markov head builders move to the file of their
graph, and the DFlash2 local conv run by build_layers to dflash2.cpp.
build_arch_graph dispatches on the backbone, then on the head.

The op order and the tensor names are unchanged.

* speculative : split the DFlash driver into a class per head

common_speculative_impl_draft_dflash stays the DFlash implementation and
becomes the base of draft_dspark, draft_dflash2 and draft_lilicorr. Its
protected constructor only reads the draft metadata; init() then sets up
the contexts with the options of the draft (draft length, backend
sampling, device features, masked h_nextn). Each derived class overrides
draft() with the path of its head from the former draft(). DFlash2 also
overrides begin() to reseed its generator per request, and LiliCorr
overrides process() to store the context features of each injected
chunk, which its noise block carries as its state.

The factory keeps the current routing: draft-dspark picks DSpark,
draft-dflash picks DFlash2 or LiliCorr from the draft metadata and
DFlash otherwise. draft-dspark with a DFlash2 or LiliCorr draft now runs
the DSpark reader instead of a mix of both. sample_from_anchor is logged
by DSpark only.

* speculative : add the draft-dflash2 and draft-lilicorr types

draft-dflash2 and draft-lilicorr name the DFlash2 and LiliCorr drafts,
which draft-dflash keeps running too: it picks them from the draft
metadata. draft-dflash2 and draft-lilicorr must match the draft model,
draft-dspark rejects a DFlash2 or LiliCorr draft, a model that is not a
DFlash draft is rejected, and a run uses at most one DFlash family type;
these errors leave speculative decoding uninitialized.

The type detected from the draft GGUF is now the concrete one, and
draft-dflash2 and draft-lilicorr download the dflash sidecar.

* docs : describe the DFlash2 and LiliCorr drafts

Add the DFlash2 and LiliCorr sections and the new types, and explain
that draft-dflash also runs DFlash2 and LiliCorr drafts.

* speculative : drop the unused DFlash is_mrope

Nothing reads it since the migration to common_batch (#29385), which
picks the number of M-RoPE position rows from the rope type of the draft.

* doc: update spec dec

* address review comments
2026-11-14 09:49:27 +01:00
o7siandPiotr Wilkin 108f73adfe grammar : optimize matching with left factoring (#29557)
* grammar : limit the number of alternatives

* grammar : introduce an AST for grammar parsing

* grammar : revert AST refactor and alternatives limit

This reverts commits:
- 84f3b57c4d6c482e7187a30735d16b02de3784fa
- 393a707ebb7e6f798abdb8af34cb1bc102f4aaa6

* grammar: optimize big grammar matching by using left-factorization

* grammar : preserve character class boundaries during left factoring

* grammar : prevent infinite expansion during left factoring

* grammar : use ASCII characters in comments

* grammar : test empty suffixes after left factoring

* grammar : deduplicate left factoring logic

* grammar : add comments

* grammar : use number parameters and clarify RSS output

* grammar : clarify character class test names

* grammar : remove performance benchmark

* grammar : share immutable rules

---------

Co-authored-by: Piotr Wilkin <piotr.wilkin@syndatis.com>
2026-11-13 13:52:21 +02:00
Aman Gupta 951d465f5c llama: move moe-cache code out of llama-graph (#32157) 2026-11-13 18:48:29 +08:00
Georgi Gerganov 8ca5a8008b llama : prune (#30565)
* llama : remove deprecated `llama_set_warmup`

Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4.1-Flash-1017-GGUF (Mac Studio, M5 Ultra, 256GB)

* llama : remove remaining deprecated API

Drop the APIs marked DEPRECATED in llama.h, the deprecated
llama_context_params::defrag_thold field and the --defrag-thold option.

Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4.1-Flash-1017-GGUF (Mac Studio, M5 Ultra, 256GB)

* fit-params : remove stale `llama-ext.h` include

Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4.1-Flash-1017-GGUF (Mac Studio, M5 Ultra, 256GB)

* llama : document `llama_model_dflash_selector_top_k`

Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4.1-Flash-1017-GGUF (Mac Studio, M5 Ultra, 256GB)

* llama : promote the NextN / speculative API from `llama-ext.h`

Move the NextN, layer input, embd row and state row APIs to `llama.h`
and rename `llama_set_embd_state_src` to `llama_set_ctx_state_src`, with
the internal `llama_context::set_state_src` following the same name.

Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4.1-Flash-1017-GGUF (Mac Studio, M5 Ultra, 256GB)

* llama : polish the NextN API promotion

Move the NextN draft model queries next to the Adapters section, rename
the `src` parameters of `llama_set_ctx_state_src` and
`llama_context::set_ctx_state_src` to `ctx_src`, and drop the now-redundant
`llama-ext.h` includes from `common/speculative.cpp` and `tools/imatrix`.

Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4.1-Flash-1017-GGUF (Mac Studio, M5 Ultra, 256GB)
2026-11-12 20:59:09 +02:00
Oliver Simons 3ba1ce0e28 qwen3.5: merge tensors on convert also (#32102)
* qwen3.5: merge tensors on convert also

* Remove conversion test for qwen3.5
2026-11-12 15:54:58 +01:00
Aman Gupta 3bce8bd50c ggml-backend : prefetch only inputs computed by earlier splits (#32100)
* ggml-backend : prefetch only inputs computed by earlier splits

The copy callback of a split runs after the prefetch and can write tensors that a later split reads, e.g. the MoE cache uploads missed experts into its bank. A prefetch of such a tensor reads it before the write.

* llama : skip the MoE cache when its device cannot run the cached mul_mat_id

Otherwise the scheduler runs the matmul on another backend and copies the whole bank every ubatch.
2026-11-12 17:24:40 +08:00
Joel Fernandes 4fffab623e llama : avoid touching unused graph metadata pages (#32043)
Each graph result reserves metadata for max_nodes, but many graphs use
only a fraction of that capacity.  The vector resize initializes the
whole reserve and makes otherwise unused pages resident.  Allocate the
reserve with new uint8_t[] instead.
2026-11-12 09:42:45 +02:00
Georgi Gerganov cb44fdb189 llama : reuse graph result instances across scheduler reserves (#32089)
Allocate gf_res_reserve and both gf_res_prev entries once in the llama_context constructor. Add llm_graph_result::set_max_nodes() and reset the existing instances in sched_reserve() instead of recreating them. get_gf_res_prev() now only selects the arena for the current batch.

Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4.1-Flash-1017-GGUF (Mac Studio, M5 Ultra, 256GB)
2026-11-11 19:58:39 +02:00
Georgi Gerganov ccd360f060 llama : remove non-fused GDN and ubatch-dependent graph nodes (#32078)
- remove build_delta_net_chunking and build_delta_net_autoregressive
- always use the fused gated delta net
- make graph_max_nodes independent of the ubatch size
- drop the fused GDN probes and fused node tags

Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4.1-Flash-1017-GGUF (Mac Studio, M5 Ultra, 256GB)
2026-11-11 15:16:16 +02:00
Oliver Simons 202c1a229f llama : Add FP8 KV-cache support (#28392)
* Add FP8 KV-cache support

* Add tests for scaled, FP8 KV-cache to test-backend-ops

* Fix get_*_scale mapping and dequnatize FP8 also before rope shift

* Normalizes cache-scale names independently of projection layout.

While fused KQV is currently impractival for non-shared scales, this is
an improvement for future use regardless

* Enable Gemma 4 Assistant with FP8 by storing and fetching scale ptrs

* Update comment wording

* Move E2E FP8 KV cache tests to test-llama-archs

They belong there as they are not just a test for ggml's backend ops

* Increase support surface, remove seed

* make scaled kv generic

* Fix CI failings for test-kv-cache

https://github.com/ggml-org/llama.cpp/actions/runs/38718763447/job/116367842578?pr=28392

* CI: execute kv-cache-scale tests

* exclude fp8-kv tests from OpenVINO

* Fix linting errors of test_kv_cache_scales

* Disable kv-ffload=false + multi-GPU tests for FP8

See https://github.com/ggml-org/llama.cpp/actions/runs/38952722084/job/117148353699?pr=28413

* Adjust test label for test-kv-cache.cpp

* Fix conflict-resolution mistakes in test-kv-cache.cpp

https://github.com/ggml-org/llama.cpp/actions/runs/40554674463/job/122367426461?pr=28392

* Move KV tests to test-fp8.cpp

https://github.com/ggml-org/llama.cpp/pull/27512#discussion_r4410518158

* Remove tmp file for test-kv-cache-scales.py on Windows as well

* Fix fp8 kv cache test by population kv_source_impl

* Exclude models that consume KV cache directly

* Remove obsolete comment

* Allow BF16 scales as well for KV cache

* Rename *_cache_scale to *_cache_s

https://github.com/ggml-org/llama.cpp/pull/28392#discussion_r4517194999

* Move `is_type_scaled()` to `llama-kv-cache.cpp`
2026-11-10 18:08:32 +02:00
Georgi Gerganov e24d0b4c34 Merge pull request #32015 from ggml-org/gg/fix-sampling-output-aliasing 2026-11-10 17:12:27 +02:00
Georgi Gerganov 3e86ce2c2d llama : reuse backend scheduler when sched_params are compatible (#32009) 2026-11-10 17:10:11 +02:00
Georgi Gerganov 40f4f4ac9d graph: mark every sampling chain as an output to prevent aliasing
The sampling chains are read on the host after the graph compute, and the
graph addresses are reused across builds with different selected rows: the
token-generation reserve graph has one output row per sequence, while the
actual block draft has n_max rows per sequence. The reserve allocates the
unselected chains without keeping them, so their buffers alias, and the
actual graph then reuses those addresses by node index.

set_outputs only marked the tensors stored for the selected rows, so the
unselected per-(sequence, row) chains were freed and reused. Collect every
chain tensor in t_sampling_all and mark all of them as outputs there.

Reproduces with -np 2 (non-unified KV) and 2 concurrent requests for
draft-dspark, draft-dflash and draft-eagle3; with different prompts one
sequence's acceptance collapses (eagle3 0.15 vs 0.40). After the fix:
dspark 0.71/0.78, dflash 0.56/0.44, eagle3 0.35/0.42.

Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4.1-Flash-1017-GGUF (Mac Studio, M5 Ultra, 256GB)
2026-11-10 14:44:14 +02:00
Alexey Kopytko 940a30ee3b model : stop renaming the recurrent cache tensors in plamo2 (#31984) 2026-11-10 17:42:30 +09:00
Oscar M. Herrera 58e38bdf65 llama : apply the iGPU lazy-mode fallback only when mmap is off (#31957)
On a device without mmap support, --lazy-mode auto resolved to off even
with --load-mode mmap, so llama_prefetch_rows never ran and the rows of
the large tensors faulted in one page at a time. Resolve it to off only
when mmap is off; the default iGPU load path is unchanged.

Fixes #31943
2026-11-10 14:55:46 +08:00
Piotr Wilkin (ilintar)andXuan Son Nguyen 5f490d7bfe feat: external PLE file loading (#31185)
* model : allow loading external PLE files

Assisted-by: Codex

* convert : add separate PLE exports

Assisted-by: Codex

* tests : fix PLE export test lint

Assisted-by: Codex

* model : make --ple an alias of --shard, allow multiple shard locations

Reuse the multi-shard loading path for external PLE files instead of a
separate option.

* --ple is an alias of --shard: both take a comma separated list and may
  be given more than once, and the shards may live anywhere
* metadata comes from the main file; numbered shards are still
  auto-discovered and strictly validated
* explicit files outside the discovered set are appended as extra shards,
  exempt from split.no and split.count checks
* -isnm/--ignore-shard-num-mismatch loads only the given files, in order,
  with no auto-discovery and no split metadata validation
* ple_path, path_ple and llama_model_loader::add_ple_file are removed;
  common_model_load() uses llama_model_load_from_splits for two or more
  paths
* common/fit.{h,cpp} take the shard path vector, so --fit and the router
  memory measurement load every shard

Assisted-by: GPT-6-Astra

* rm -isnm

* make sure to dedup paths

* rm test_convert_ple

* address comments

* allow ple shard to override tensor

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2026-11-09 19:41:01 +01:00
Julius TischbeinandOliver Simons 9d340ec341 Windows unbuffered model load (#26014)
* Windows unbuffered io

* Fix read len calculation

* Add test and model load timing

* chunked fallback read + removing filepointer semantic divergence between linux and windows

* tests : remove unused mmap test arguments

Assisted-by: Codex

* remove timing, set file pointer after chunk read, test refinement

* Update tests/test-llama-mmap.cpp

Co-authored-by: Oliver Simons <osimons@nvidia.com>

* Update src/llama-mmap.cpp

Co-authored-by: Oliver Simons <osimons@nvidia.com>

* test refinement

Assisted-by: Codex

* remove duplicate constexpr

Assisted-by: Codex

* adding label behavior to tests

Assisted-by: Codex

---------

Co-authored-by: Oliver Simons <osimons@nvidia.com>
2026-11-09 19:22:08 +01:00
Aman Gupta a8fad21e99 mtp: read the target hidden states from a device buffer (#31927) 2026-11-09 20:52:32 +08:00
jjperry69andGabe Goodhart 0c6dca2fae models : Attach Granite NVFP4 weight scales (#31449)
* models : Attach Granite NVFP4 weight scales

* feat: Pass nvfp4 scales through build_ffn for all granite architectures

Branch: granite-nvfp4-moe-scales
AI-usage: full (Claude + Sonnet 5.5)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

---------

Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>
2026-11-09 13:04:06 +01:00
Xuan-Son Nguyen 7d7f028753 mtmd: refactoring: remove clip.h, consolidate code into mtmd (#31865) 2026-11-08 15:49:06 +01:00
Alexey Kopytko cf34d31133 moe-cache : ensure CPU part does not wait for the cached experts (#31888) 2026-11-08 22:29:11 +09:00
PascalandGeorgi Gerganov d6be065572 llama, mtmd: follow the reference precision of ggml_prec_set_acc calls (#31851)
* llama, mtmd: follow the reference precision of ggml_prec_set_acc calls

Requests that the reference implementation does not keep in F32 move
to GGML_PREC_BF16: the GLM4 family down and output projections, the
MiMoVL vision matmuls and the Qwen3-TTS speaker encoder conv1d. The
DeepSeek V4/V4.1 routers and the MiniMax-M3 indexer stay in F32 with
a link to the reference line that computes them in F32.

* ggml: handle GGML_PREC_BF16 the same way as GGML_PREC_F32 in backends

Backends that reject GGML_PREC_F32 on the src1 of MUL_MAT_ID now also
reject GGML_PREC_BF16 (CUDA, Hexagon, OpenCL, WebGPU, Vulkan), and
backends that accept GGML_PREC_F32 for flash attention now also accept
GGML_PREC_BF16 with the same F32 accumulation (CPU, SpaceMIT, ET).
Vulkan keeps the F32 transfer between devices for both. The CUDA
cuBLAS path already handles GGML_PREC_BF16 and is unchanged.

* tests: cover GGML_PREC_BF16 in the flash attention tests

The flash attention cases run with GGML_PREC_BF16 next to F32 and
DEFAULT, and var_to_str prints bf16 so these cases keep their own name.

* llama: request GGML_PREC_BF16 for the KQ multiplication

* cont : add TODO in clip.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-11-08 08:37:46 +01:00
e95426f169 llama_moe_cache: run missed experts on CPU, add tuning script (#30966)
* moe-cache : compute part of the misses on the CPU

--moe-cache-cpu-share F computes a share F of the MoE cache misses on the CPU
from the host experts instead of uploading them. The graph builds the expert
FFN twice: on the device from the cache slots, where the misses left to the CPU
read zero slots, and on the CPU from the host experts, where the experts
computed on the device have id -1. The two results are added before the down
bias.

- ggml-cpu: MUL_MAT_ID skips negative ids and writes zero rows
- sched: the copy callback is called for all the inputs of a split, and before
  the host sync when there are no events
- the slot lookup callback reads the inputs of the CPU part together with the
  selected experts, so the CPU part does not wait for the device, and its
  result is copied back asynchronously
- each token uses distinct zero slots, mul_mat_id does not support an expert
  selected twice by a token
- LLAMA_MOE_CACHE_TRACE writes the selected experts of each lookup, for a
  simulator of the cache

* scripts : add moe-cache-tune.py to pick the MoE cache arguments

The script wraps a llama-server command: it starts the server at two cache
sizes and three CPU shares, fits the upload and CPU speeds of the machine, and
replays the routing of the runs through a copy of the cache logic to predict
other sizes and shares. It prints the recommended --moe-cache-mib and
--moe-cache-cpu-share.

docs/moe-cache.md describes the MoE cache arguments and the script.

* add am17an as codeowner for MoE cache

* moe-cache : upload all the misses until the cache is full

With a high --moe-cache-cpu-share, few misses are uploaded, so an empty cache
fills slowly and more misses than needed go to the CPU. The CPU share now
starts once all the slots of a cache group hold an expert. moe-cache-tune.py
replays the same rule.

* add backend sync for async transfer queue

* moe-cache : let the scheduler copy the results of the CPU part

* Fix MSVC compilation

* remove sync change

* llama-graph : extract the CPU share condition into can_cpu_share

* llama-graph : make llm_graph_params::moe_cache const

The graph construction no longer updates the MoE cache directly: the CPU
parts of the layers are accumulated in the graph result and applied to
the cache in llama_context::process_ubatch, after the graph inputs are
set and before the graph is computed.

Assisted-by: dsh:llama.cpp/ggml-org/GLM-5.3-Flash-GGUF (Mac Studio, M5 Ultra, 256GB)

* scripts : replay the ClassLRU policy in moe-cache-tune.py

* moe-cache : pick CPU misses by CRF instead of random (#31853)

* moe-cache : remove the backend logic of the CPU part from the graph

The CPU part reads the host experts, so the scheduler places it on the
CPU without set_tensor_backend. The cache gives no CPU map for batches
that a device would offload. Graphs with a CPU part look up their own
slot map, so the graph does not register the part with the cache.

ggml-backend : the inputs of the next split that are already computed
are copied to host memory before the current split runs, so a CPU split
does not wait for the device split before it. This replaces the stash
of the cache, and the copy callback is again called for host weights
only.

* llama-graph : return the MoE cache slots and CPU ids in a struct

The scheduler prefetch no longer checks that the next split runs on
another backend: the inputs of a split are never on its own backend,
so the input loop already skips that case.

---------

Co-authored-by: Gaurav Garg <gaugarg@nvidia.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Alexey Kopytko <alexey@kopytko.com>
2026-11-08 00:20:58 +08:00
Adrien Gallouët c0ab6e5c0b llama : add missing link to pthread (#31785)
* llama : add missing link to pthread

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Link Threads::Threads privately

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

---------

Signed-off-by: Adrien Gallouët <angt@huggingface.co>
2026-11-07 08:43:50 +02:00
usrlocalben bcb0152876 model: add Kimi-K3.1-Pro text model (#31779)
* model: add Kimi-K3.1-Pro text model

K3 with the full-attention MLA layers replaced by DSA: on this checkpoint 24
of the 93 layers carry a lightning indexer (32 heads x 128, top_k 2048, no
rope). The KDA (linear-attention) layers and the rest of the K3 skeleton -
cross-layer residuals, latent MoE, situ, MLA output gate, full-rank KDA gate -
are unchanged, so this reuses the K3 graph and converter and adds the indexer.

Indexer:
  - the selection is an additive mask over the whole cache, not a gather of
    the top-k rows, so it reuses the existing sparse flash attention path;
    off that path the mask stays correct but still costs a kq over the cache
  - the indexer key LayerNorm takes its eps from the model's rms_norm_eps,
    because dsa_config declares no eps of its own

Graph and cache:
  - new arch with four indexer tensors per DSA layer, and a hybrid memory
    that keeps a K-only MLA cache for those layers, recurrent state for the
    KDA layers, and the indexer key cache
  - the graph node budget shares the K3 entry

Conversion:
  - KimiK31Model(KimiK3Model), picked by KimiK31ForConditionalGeneration
  - dsa_config becomes attention.indexer.{head_count,key_length,top_k,types}
    plus the indexer LayerNorm eps; the layer list is 1-indexed like
    linear_attn_config's, and the converter asserts that it covers exactly
    the full-attention layers
  - the routed experts stay MXFP4 and are repacked as in K3, not dequantized
  - the vision tower and mm_projector are skipped: text only for now
  - the arch key follows the checkpoint's own model_type ("kimi_k31") and the
    loader registers KimiK31ForConditionalGeneration; the release name carries
    a -Pro suffix that nothing in the config or the tensor names uses

Quantisation: the indexer's q_b, k and proj are kept out of the quant
overrides, since the top-k selection is sensitive to their precision.

Verified on an 8-layer slice against the HF checkpoint: 38 tensors checked
exactly, the indexer metadata against the config, and the selection against
full attention - identical PPL at top_k beyond the context length, divergent
once top_k is forced below it. Arch test fixture and the full arch suite pass.

* converter: avoid clutter in the k3 base

* narrow comment to match model

* update metal fusion expectations

* restore

* sync with PR 31733 refactoring
2026-11-06 23:42:46 +01:00
Alexey Kopytko c4fb579695 moe-cache : LRFU/MQ-like hybrid cache, ClassLRU (#31233)
* moe-cache : LRFU/MQ-inspired hybrid cache

* make the clock advance by N tokens: use the real token count (ne[1] is always 1, ids have n_expert_used entries per token)

* sel is a RESHAPE node, the orig input is in src[0], so sel->src[0]->ne[1] is the count

* c for the class index, last_use for last use time

* explain the roles of these

* compute the key once

* use the key directly instead of re-reading

* show how the score is computed from the age

* remove the branch and clarify exp2 and log2 relationship

* reword the header comment and elaborate on unused slots and sorting

* not a copy, not just skip

* std::array maybe

* Revert "std::array maybe"

This reverts commit 7649b1f172db4941a854ad115bec0c7e062b65b9.

* half life it is

* add key and iteration helpers

* extract decayed_crf

* bump classes to 8, document the formula, display the cache size in token worth count

* assert the computed number of classes matches the half life
2026-11-06 11:32:54 +02:00
Xuan-Son Nguyen 6023692b1e llama: fix kv shifting, add tests, add per-model build_rope (#31683)
* llama: fix kv shifting and add tests

* llama: add graph build_rope (#31693)

* llama: add graph build_rope

* improve

* migrate new models

* update review skill

* fix ci

* add --kv-shift to CI
2026-11-05 21:10:36 +01:00
Xuan-Son Nguyen b1c902f026 llama, mtmd: (chatterbox) add use_classifier_free_guidance as gguf metadata (#31698)
* llama, mtmd: add use_cfg as gguf metadata

* use_classifier_free_guidance
2026-11-05 20:09:33 +01:00
Sigbjørn Skjæret e8df20d238 models : recursive fix (#31749) 2026-11-05 20:06:55 +01:00
fecdc81eec model : add Ripple (ricursiveai) (#31692)
* feat : added ricursiveai ripple support

* fix : mandatiry SWA, scale through helper, comments back

* fix : metal

* model : make ricursive RoPE/NoPE explicit and validate the layer pattern

Write attention.rope_pattern and read it as optional, falling back to the
sliding window pattern so existing GGUFs keep loading. Refuse a
sliding_window_pattern that does not cover every layer, a model with no
sliding layer, and a gate or value residual present in only some layers.
The converter derives layer_types when the config omits it, ignores a stale
hybrid_layer_pattern and drops tensors of features the config disables.

Assisted-by: Claude Opus 5.5

* model : make ricursive swiglu_clamp per-layer

Store swiglu_clamp as a per-layer array, read it with get_key_or_arr so the
scalar in existing GGUFs still applies to every layer, and refuse a negative
or non-finite value. Add a test-llama-archs fixture with mixed per-layer
clamps and no rope_pattern, so the saver roundtrip checks both.

Assisted-by: Claude Opus 5.5

* model : use the ricursive per-tensor scales and RoPE parameters

Pass the attn_gate and output weight scales to build_lora_mm, take
ext_factor and attn_factor from the graph instead of hardcoding them, and
copy rope_freq_scale_train to the SWA layers instead of pinning it to 1.
Cite the reference lines for the value residual and the NoPE layers.

Assisted-by: Claude Opus 5.5

* convert : drop the ricursive chat_template.jinja override

The precedence between tokenizer_config.json and chat_template.jinja is to
be changed in SpecialVocab for all models instead. Until then a new
conversion stores the short tokenizer_config.json template; GGUFs that
already carry the tool-aware template are not affected.

Assisted-by: Claude Opus 5.5

* fix : remove NVFP4 checkpoint quantization block

* match #31733 refactor

---------

Co-authored-by: Piotr Wilkin <ilintar@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
2026-11-05 19:55:15 +01:00
45b6604b20 model: Add support for the xing4_0 (#31589)
* model: add support for Xing4.0

* Update src/models/xing4_0.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

* Update src/models/xing4_0.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

* Update src/models/xing4_0.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

* Update src/models/xing4_0.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

* Update src/models/xing4_0.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

* Update src/models/xing4_0.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

* fix: rename model file to xing4-0.cpp to match CI expectations

* model: rename xing4_0.cpp to xing4-0.cpp

* lint: fix E128 continuation indent in conversion/xing.py

* tests: add xing4_0 fusion baseline for Metal

* reduce comments

---------

Co-authored-by: shixq7 <shixq7@chinatelecom.cn>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
2026-11-05 17:47:27 +01:00
Xuan-Son Nguyen e0f96a1a12 llama: refactoring: move model to class member of llm_graph_context (#31733) 2026-11-05 15:41:03 +01:00
Pascal 040ce199a1 graph: store the MTP conv snapshots of every recurrent model in one set_rows (#31660)
* graph: store the conv state of every rollback arch in one set_rows

The rollback slots of the causal conv history were written with one
copy per slot in qwen4exp, glm5-next, kimi-k3, bailingmoe3, lfm and
mamba2, while delta_net already wrote them with a single set_rows.
build_conv_state_store now does this for all of them: one copy without
rollback, otherwise one set_rows of the overlapping windows into the
min(n, n_rs_seq + 1) slots a rollback can read.

The slot order {n_rs_seq, ..., 0} is computed once per graph and each
conv layer takes a view of its tail. Its size does not depend on the
ubatch, so the reserved graph covers every ubatch shape, and the graph
input that held it is gone.

A model that is not causal never rolls back, so the context clamps
n_rs_seq to 0 for it, like for an arch without rollback support.

* nits: compute the conv slot order in the graph and keep the n_head name of bailingmoe3

* graph: build the conv slot order in each conv layer

The slot order {K-1, ..., 0} of the conv state store was one tensor
shared by every conv layer of the graph, built on the device of the
first one, so each layer on another device copied the view of its
tail. Each conv layer now builds its own order next to its set_rows,
and llm_graph_input_rs no longer holds it.
2026-11-05 09:28:03 +01:00
Daniel Bevenius 330f0189c9 qwen2 : add nvfp4 scales to build_ffn (#31657)
This commit adds nvfp4 scales to qwen2's build_ffn call which are
currently passed as NULL.

The motivation for this is that a model converted to NVFP4 will
currently crash because the scales are loaded but never applied in
the FFN:
```console
llama-completion: llama.cpp/src/llama-sampler.cpp:1218:
void llama_sampler_dist_apply(llama_sampler*, llama_token_data_array*):
Assertion `found' failed.
```
The attention already applies its scales but ffn is missing them.
2026-11-05 06:29:50 +01:00
Hongqiang Wang e56f006ed6 llama : fix on-device state copy sizes for quantized KV caches (#30541)
* llama : fix on-device state copy sizes for quantized KV caches

The on-device sequence state copies (LLAMA_STATE_SEQ_FLAGS_ON_DEVICE) computed
their element count as size / ggml_element_size(). For a quantized type such as
q8_0 or q4_0 that is the number of blocks, not elements, so only part of each
range was copied: the restored state was wrong, or the copy crashed.

Compute the count as size / ggml_type_size() * ggml_blck_size() for the save,
the restore and the copy between differently chunked ranges, and assert that
each range covers whole blocks.

* llama : drop the one-line comments

* llama : drop the redundant cast in the state copy size
2026-11-05 10:31:01 +08:00
Aman Gupta e853ec9a8c llama : follow ctx_other devices and flash attention in Gemma4 assistant (#31635)
* llama : follow ctx_other devices and flash attention in Gemma4 assistant

* llama : include <algorithm> for std::any_of
2026-11-04 11:23:25 +02:00