Commit Graph
35 Commits
Author SHA1 Message Date
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
Sigbjørn Skjæret 582eab7186 ci : bump ty to 0.0.100 (#32030)
* bump ty to 0.0.100

* rename rules

* type fixes

* type fix

* proper type fix
2026-11-10 21:54:14 +01:00
Xuan-Son NguyenandPascal 9f0e5098a5 mtmd: support MageVL-Cowork model (#31819)
* mtmd: support MageVL-Cowork model

* mtmd: keep magevl rope_freqs at model level and check its shape

The rope factors are shared by every layer, so they live in clip_model
instead of a pointer copied into each clip_layer. The loader now checks
that v.rope_freqs is F32 with d_head elements and that d_head splits
into the 4:6:6 pairs the graph expects.

---------

Co-authored-by: Pascal <admin@serveurperso.com>
2026-11-07 19:36:44 +01:00
Oliver SimonsandSigbjørn Skjæret 68d20b884c Quant: OCP FP8 E4M3 support (#27512)
* WIP OCP FP8 E4M3 support

* Fix python type-checker

* Materialize input_scales also for FP8 when converting

* Fix conversion of https://huggingface.co/RedHatAI/Qwen3.8-27B-NVFP4

1. Per row FP8 wrongly fell to NVFP4 conversion, as NVFP4 checked on
   dims alone. Also check on dtype for FP8
2. Need to reshape FP8 QKV projections scales in the same way that
   weights are reshaped

* Allow remaining FP8 tensors to be dequantized during conversion

* Allow tensor-strategy for FP8-only compressed-tensor ckpts

* Fix and test gguf-py behavior for FP8_E4M3

* Disallow QKV-fusion for FP8 temporarily

* Fix conversion of fused qkvz & FP8 for Qwen3-Next

* Avoid fusing FP8 for --fuse-gate-up-exps as we may have different ws

* Emit warnings when not fusing FP8 during conversion

* More FP8 conversion fixes

* Add supported for strided copies to/from FP8 in CPU

* remove unneeded scratch buffer from FP8 cpu cpy/dup path

* add explanatory comments and TODOs

* Add dedicated encoder and decoder tests for FP8

* Whitelist ggml_op_get_rows in metal instead of blacklisting

required to fix failing CI, and white-listing should be more
future-proof than adding FP8 to the black-list

https://github.com/ggml-org/llama.cpp/actions/runs/38433916498/job/115422880633?pr=27512

* Fix more conversion bugs

* Defer weight materialization during conversion

* Blacklist fp8 in metal backend instead of white-list

* Adjust indents

* Fix lint + execute tests

* Add fast CPU kernel for F8_E4M3

* Conversion fixes

* Fix remaining gaps

* Enable tied weights with shared scales

* Make mandatory-F32 rules apply to FP8 during conversion

* Fix python type checks

https://github.com/ggml-org/llama.cpp/actions/runs/39765670052/job/119780379595?pr=27512

* Fix kaleidai unit-test failures

https://github.com/ggml-org/llama.cpp/actions/runs/39765670125/job/119780383150

* Relax numeric precision constraints for pre-check

* Leave fast-FP8 CPU on RISC-V for follow-up

We already exclude arm from the fast-path

* Allow output scale tensors to be located in any gguf shard

* Move test_conversion_fp8.py test execution to behavior-check.yaml

* Apply batched suggestions from code review

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

* Move mixed compressed-tensor logic into dequant_fp8 + add unit-tests for it

* Install all requirements also on Windows for behavior-check

Fixes https://github.com/ggml-org/llama.cpp/actions/runs/40535852590/job/122300758223?pr=27512

* Unmap lazy tensors before clean-up in Windows

Should fix https://github.com/ggml-org/llama.cpp/actions/runs/40539797824/job/122314782459?pr=27512

* LF line endings

https://github.com/ggml-org/llama.cpp/actions/runs/40539798168/job/122314791118?pr=27512

* Extract FP8 tests from llama-arch to its own test-fixture

See https://github.com/ggml-org/llama.cpp/pull/27512#discussion_r4400628221

* Update gguf-py/gguf/scripts/gguf_convert_endian.py

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

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
2026-10-29 18:14:37 +01:00
tc-mbandXuan Son Nguyen 7eed6b7685 model: Add MiniCPM-OCR-Jev (#30980)
* model : add MiniCPM-OCR-Jev support

The model is a Qwen3.5-VL trunk with a value head read at the last token: it
scores an OCR text against an image rendered from it, it does not generate.

Add the openbmb-minicpm-ocr-jev decision type, served by POST /v1/systemone.
The class scores are the pooled output of the sequence, read with last pooling,
so the conversion turns score.weight into cls.output and sets
embedding_length_out. The checkpoint has no LM head, so text generation is
rejected instead of using the output weights duplicated from the token
embeddings.

The task is fixed, so its prompt is entirely in the systemone template, the
same way h2o-lightning keeps its default there. The processor of the checkpoint
allows up to 16384 merged tokens per image, more than the Qwen-VL default of
mtmd, so the mmproj keeps the image budget of the preprocessor config. The
checkpoint declares MiniCPMOCRForSequenceClassification in its config.json, as
other models do.

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* fix code

Signed-off-by: tc-mb <tianchi_cai@icloud.com>

* use gguf meta classifier_output_labels

* remove redudant code changes

---------

Signed-off-by: tc-mb <tianchi_cai@icloud.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2026-10-27 11:49:12 +01:00
Kashif RasulandSigbjørn Skjæret 4c3c5810f8 hybrid dna tokenizer fixes (#30825)
* vocab : support Carbon-14B HybridDNA tokenizer

Carbon-14B auto-tags untagged DNA runs and uses N-padded tail tokens
(tail=pad_n). Also strip whitespace inside <dna> tags and handle a stray
</dna> like the HF tokenizer.

* convert : fix special tokens and merges for older Carbon models

Carbon-500M/3B/8B don't register the Qwen added tokens and ship no
tokenizer.json, so take the token types, merges and special ids from the
base tokenizer.

* Update conversion/base.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-vocab.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-vocab.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-vocab.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update conversion/base.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update conversion/base.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update conversion/base.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* address review comments

* Update src/llama-vocab.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2026-10-19 23:01:40 +02:00
fzowlandSigbjørn Skjæret 412a363c65 qwen3 : bidirectional attention and dense_2 output projection (#30607)
* qwen3 : bidirectional attention and dense_2 output projection

Assisted-by: Grok

* convert : read use_bidirectional_attention in base

Assisted-by: Grok

* Update conversion/base.py

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

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
2026-10-19 09:29:02 +03:00
bri-prismandGeorgi Gerganov a9d27ac693 model : support for Prism Bonsai 2 27B (#29600)
* Runtime support for Prism Bonsai 2 27B

Assisted-by: Claude Code

* address prism hadamard runtime feedback

* move hadamard tensors into method, define folded weight

* load_* hadamard fixes

* cont : clean-up

* conversion cleanup

Assisted-by: Claude Code

* prism hadamard key and methods for converter

Assisted-by: Claude Code

* address review bot feedback

Assisted-by: Claude Code

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-10-11 14:39:16 +02:00
Sam Malayek 75118a3a59 convert : support Qwen3.5 embedding models (#27920)
* Update convert_hf_to_gguf: support Qwen3.5 embedding models

* Behavior-preserving refactor for conventions.

* conversion: simplify pooling comment
2026-10-08 08:40:01 +03:00
Xuan-Son Nguyen a4cb4c61fd llama, server: add /v1/systemone API (models: laya, julia-1, lev, openjev, kev) (#29818)
* init conversion

* convert: ok

* model loaded

* add server code

* improve conversion script

* support shared prompt prefix

* add docs, imorove UX a bit

* add vision support

* add openjev tiny model for testing

* add dev docs

* support lev & kev

* clean up

* fix lev noul

* fix py lint

* nits docs

* clarify about not supporting date_facts
2026-10-02 11:56:04 +02:00
Yu Chengye 2b36825cbc convert : write Gemma embedding scale for DFlash drafts (#29802)
* convert : write Gemma embedding scale for DFlash drafts

A DFlash draft shares the target's token embeddings. Gemma scales them by sqrt(hidden_size) in the forward pass, and the draft config does not state that scale, so the converted draft read unscaled embeddings.

Take the scale from the target config when the draft config has none.

Assisted-by: Claude

* convert : check with get_model_architecture for gemma models
2026-10-01 16:34:32 +02:00
b016f461be convert : fix LoRA conversion crash for Qwen3.5 V-head reorder (#28324)
* convert: fix LoRA conversion crash for Qwen3.5 V-head reorder

_reorder_v_heads does reshape+permute+reshape to reorder V heads from
grouped to tiled order.  LoraTorchTensor.reshape() cannot split its
row dimension (A matrix), so converting Qwen3.5 LoRA adapters that
target out_proj crashes with NotImplementedError.

Fix: detect LoRA tensors and apply the equivalent index permutation
directly — column reorder (dim=last) permutes A's columns, row
reorder (dim=0) permutes B's rows.  This is mathematically identical:
  (B @ A)[:, perm] == B @ A[:, perm]
  (B @ A)[perm, :] == B[perm, :] @ A

Verified: both paths produce exactly zero diff against the full-tensor
reorder on random (rank=32, 4096×4096) matrices.

Fixes #21125

Signed-off-by: Radu Swigler <radu@swigler.com>

* convert: add ty: ignore for hasattr-guarded LoRA call

Assisted-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix comment

* nowrap

---------

Signed-off-by: Radu Swigler <radu@swigler.com>
Co-authored-by: Radu Swigler <radu@swigler.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
Assisted-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-09-30 19:30:21 +02:00
Georgi GerganovandSigbjørn Skjæret 22bdcc4cdd mimo : support dflash (convert + feature extraction) (#29650)
* convert : update to support dflash

* cont : fix

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

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
2026-09-30 17:04:35 +03:00
Tarek Dakhran bd4f514db1 convert : allow vision target for DFlash/Dspark (#29339)
Resolve the target arch with get_model_architecture so vision targets
(e.g. Lfm2VlForConditionalGeneration) map to their text model for the vocab.

Fix double rope reorder for LFM2/LFM2.5 DSpark drafters
2026-09-24 01:16:43 +02:00
Hrishith Thadicherla 633733d0ae model : support Gemma4 DSpark draft backbone (#29226)
* dspark: add Gemma 4 draft support

Add GGUF conversion and runtime support for full-attention and SWA Gemma 4
DSpark drafts, including tied output weights and boolean backbone metadata.

Assisted-by: Codex

* dflash: infer Gemma draft features from metadata
2026-09-23 13:34:09 +03:00
DevVexusandClaude Opus 5 9a7570587c convert : write explicit recurrent_layers for Qwen3-Next / Qwen3.5 (#28208)
Problem
- Loader prefers `<arch>.attention.recurrent_layers`, falls back to `full_attention_interval` if missing
- Converter only ever writes the interval. gguf-py has no constant/writer for the array
- Interval can only describe evenly spaced full-attention layers. Any non-uniform `layer_types` gets reconstructed wrong
- No error, no warning. Model loads, runs, wrong layers get wrong ops. Full-attn layers marked recurrent lose their KV cache
- Every published Qwen3.5 checkpoint is uniform so nobody's hit it yet

Repro
12 layers, periods 4/3/5:

    layer:  0 1 2 3 4 5 6 7 8 9 10 11
    actual: L L L F L L F L L L  L  F
    loader: L L L F L L L F L L  L  F
                        ^ ^

Layer 6 is full attn, loaded as recurrent. Layer 7 the reverse.
52-layer non-uniform stack: 15/52 mis-typed.

Fix
- `constants.py`: add `Keys.Attention.RECURRENT_LAYERS` (name already registered in llama-arch.cpp)
- `gguf_writer.py`: add `add_recurrent_layers()`, same shape as `add_rope_pattern()`
- `conversion/qwen.py`: emit array from `layer_types` in `Qwen3NextModel.set_gguf_parameters` (covers 3-Next, 3.5, 3.5-MoE)

Notes
- Array is padded with `false` for MTP blocks. `get_key_or_arr` checks length against `n_layer_all`, which includes MTP. Matches the fallback's `i < n_layer()` guard
- Interval is still written. Old builds only understand the interval
- `layer_types` length != `num_hidden_layers` now raises in converter instead of producing a GGUF that fails at load

Tested
- End-to-end on a 62-layer non-uniform Qwen3.8-27B (2 linear layers removed). Loader reads the array, 62 blocks, 0 mismatches. Without fix: interval fallback, mis-typed
- MTP padding NOT tested on a real MTP model. Reasoned from qwen35.cpp + get_key_or_arr. Would appreciate a check

Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-09-07 10:12:50 +03:00
ca3d5a3e10 model: add DSpark support for Nemotron3.5 (#27804)
* model: add DSpark support for Nemotron3.5

* Update src/models/dflash.cpp

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

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2026-08-28 01:49:27 +02:00
b10f9ca58c spec : add DFlash2 support (local convolution + candidate selector) (#27342) (#27816)
* spec : add DFlash2 support (local convolution + candidate selector) (#27342)

* support DFlash2

* Add p_min in DFlash2

Assisted-by: Claude Opus 5

* Revert unnecessary changes

Assisted-by: Claude Opus 5

* Revert draft sampling in rejection sampling

Assisted-by: Claude Opus 5

* Refactor code structure

Assisted-by: Claude Opus 5

* Delete embedding scaling

Assisted-by: Claude Opus 5

* Gate output transforms on DFlash2

Assisted-by: Claude Opus 5

* Optimize Dflash 2 cost

Assisted-by: Claude Opus 5

* Avoid using atoi

Assisted-by: Claude Opus 5

* Modify comments

Assisted-by: Claude Opus 5

* Move llama_model_dflash_selector_top_k to llama-ext.h

Assisted-by: Claude Opus 5

* Formatting

Assisted-by: Claude Opus 5

* Apply patch to fix the mrope bug

Assisted-by: Claude Opus 5

* fix ci

Assisted-by: Claude Opus 5

* Fix graph number calculation

Assisted-by: Claude Opus 5

* rename hid and unary

Assisted-by: Claude Opus 5

---------

Co-authored-by: Jian Chen <jianchen0311@gmail.com>
Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>

* revert top-k.cu changes

---------

Co-authored-by: Zihan Zhang <tiancaizhangdaxian@sjtu.edu.cn>
Co-authored-by: Jian Chen <jianchen0311@gmail.com>
2026-08-27 19:17:07 +02:00
Tiwei Bie 2115b73d8e model : support DSpark for bailingmoe3 (#27508) 2026-08-22 12:19:48 +03:00
Tarek Dakhran 07822bddf8 model : support DSpark for LFM2 models (#27383) 2026-08-20 16:36:57 +02:00
9cd719af21 model: support speculators-format checkpoints for DSpark (#26275)
* dspark: support speculators-format checkpoints (SpecForge exports)

Speculators-format DSpark drafts (e.g. SpecForge exports for the
Gemma-4-26B-A4B target) differ from the dense DeepSpec checkpoints in
three ways:

- the config nests the backbone hparams under transformer_layer_config
  and gives the extract layers as aux_hidden_state_layer_ids
- the block is the DFlash 1+N fill-in layout: the anchor slot is a bonus
  token, not a prediction slot. Written as dflash.bonus_anchor; such
  drafts build the block and read the mask positions exactly like
  DFlash (n_max drafts from a 1+n_max block), only the Markov/confidence
  sampling comes from DSpark
- the draft output vocab may be reduced (draft_vocab_size < vocab_size)
  with a d2t remap table. The converter expands lm_head/markov_w2 back
  to the full vocab and synthesizes an lm_head bias of -1e9 on the rows
  the draft cannot produce, so the runtime needs no d2t remapping. Such
  drafts ship their own (now optional) token_embd/output tensors instead
  of sharing the target's

Verified against gemma4-26b-a4b-dspark: greedy outputs are byte-identical
with and without the draft; acceptance 0.46, mean draft len 3.7 (n_max 6).

Co-authored-by: desovo7 <942845546@qq.com>
Assisted-by: Claude Fable 5

* dspark: fold the speculators draft class into DSparkModel

One class now covers every DSpark variant. What used to pick the class is
a single flag, because the arch name turns out to be the only thing that
separates the two families: SpecForge also exports a flat schema that
carries no speculators_* fields yet still uses the 1+N bonus-anchor block,
so keying on those fields would silently mis-read its drafts.

Also rename i0 to i_first_pred in the draft read loop and the Markov head,
and give the head a real bonus_anchor bool instead of testing i0 > 0.

Converting the Qwen3-8B DeepSpec draft and both gemma-4 speculators drafts
produces byte-identical GGUFs. The one behaviour change is that the
markov_head_type check now also covers the DeepSpec checkpoints, which
previously skipped it.

Co-authored-by: desovo7 <942845546@qq.com>
Assisted-by: Claude Opus 5

* dspark: address review comments

- rename bonus_anchor to sample_from_anchor (GGUF key and code), matching
  the checkpoint config field; absent key still means anchor-first
- rework the reduced draft vocab to match EAGLE3: d2t is written as I64
  absolute target ids and the logits are scattered at runtime, instead of
  expanding lm_head/markov_w2 and synthesizing an output bias at conversion
- move the t2d skip to modify_tensors, like EAGLE3
- drop _is_specforge: the arch name only picks the sample_from_anchor
  default, embed/lm_head sharing is decided by the draft vocab size
- deduplicate the tok_embd create_tensor left behind by the rebase

Verified with the RedHat gemma-4-31b speculator draft: greedy output is
byte-identical with and without the draft; acceptance 0.26 (n_max 7).

Co-authored-by: desovo7 <942845546@qq.com>
Assisted-by: Claude Fable 5

* dspark: fold the sample_from_anchor read into the block_size block

* dspark: fix flake8 continuation indent

* clean up

* dspark: key the sample_from_anchor default off the export format

  Co-authored-by: desovo7 <942845546@qq.com>
  Assisted-by: Claude Fable

* dspark: drop t2d in filter_tensors

  Co-authored-by: desovo7 <942845546@qq.com>
  Assisted-by: Claude Fable

* dspark: map model.lm_head instead of bypassing the dflash prefix

  Co-authored-by: desovo7 <942845546@qq.com>
  Assisted-by: Claude Fable

---------

Co-authored-by: desovo7 <942845546@qq.com>
Co-authored-by: ruixiang63 <wangruixiang07@outlook.com>
2026-08-17 13:51:06 +02:00
Xuan-Son Nguyen fa88ae9368 convert: add @ModelBase.example (#27208)
* convert: add @ModelBase.example

* add docs

* add more variants

* BailingMoeV3ForCausalLM

* rm pocket-tts
2026-08-17 10:15:11 +02:00
lnigamandSigbjørn Skjæret cc078b45b6 Dflash support for nemotron-3.5 (#26905)
* conversion: skip untrained DFlash embeddings

* Add Nemotron DFlash support

* Add DFlash NVFP4 support

* Address review comments

* add missing output_s for nvfp4

* Include change for keeping residual for last layer also if requested in future dflash models

* Update conversion/qwen.py

Defensive check, not needed

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

* Fixing bug introduced by merge conflict

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
2026-08-11 18:46:26 +05:30
Caleb DeLeeuw b06fbc968b convert : import bytes_to_unicode from convert_slow_tokenizer (#26217)
bytes_to_unicode was removed from transformers.models.gpt2.tokenization_gpt2
in huggingface/transformers#40936, but it had already been copied into
transformers.convert_slow_tokenizer in huggingface/transformers#30334
(transformers 4.54.1), so import it directly from there.

Applies the same fix to chatglm.py.
2026-08-04 10:34:30 +03:00
Masashi YoshimuraandSigbjørn Skjæret 4ed2b13f75 model: MTP support for Qwen3-Next (#25589)
* mtp for qwen3nex

* fix for python type-check

* Fix to compute num_mtp from directly mtp layer

* define opt_num_mtp_layers in _QwenMtpMixin and fix some comments

* Fix for python type check

* Update gguf-py/gguf/constants.py

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

* rebase and add load_mtp flags

* Update src/models/qwen3next.cpp

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

* Update src/models/qwen3next.cpp

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

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
2026-08-03 17:15:01 +09:00
84075273c8 spec: add DSpark speculative decoding (#25173)
* spec: add DSpark speculative decoding

DSpark (DeepSpec, 2026) on top of the merged DFlash drafter. It reuses the
DFlash encoder/decoder graph, target feature extraction and KV-cache injection,
and the verify/accept path unchanged; the draft model is a new "dspark" arch
adding a low-rank Markov head (markov_w1/w2) and an optional (unused here)
confidence head. No new public APIs.

The proposal is the only change: the block is anchor-first (position 0 already
predicts the first draft) and the decoder graph applies a semi-autoregressive,
previous-token conditioned logit bias in-graph, chained per block position:

  logits'(i) = logits(i) + markov_w2 . markov_w1[prev(i)]
  prev(0)    = the block's anchor token, prev(i>0) = argmax(logits'(i-1))

vectorized across all blocks in the batch; the anchors are fed through a
dedicated graph input (token 0 of every block). Greedy stays lossless
(verify unchanged, same as DFlash).

- new arch "dspark" (llama_model_dspark : llama_model_dflash, reuses the graph,
  loads the markov/confidence tensors; shares the target's embed/lm_head).
- Qwen3DSparkModel converter.
- new spec type "draft-dspark" (common_speculative_impl_draft_dspark :
  common_speculative_impl_draft_dflash, overrides draft() only: submits whole
  anchor-first blocks and greedily reads back the biased logits).

* spec: read draft block size in the dflash impl

* docs: add DSpark section to speculative.md

* spec: keep dspark block size read in the dspark impl

* dspark : add TODOs for incomplete parts

- confidence head is loaded but not used yet
- confidence-scheduled prefix pruning is not implemented
- the in-graph Markov chain is greedy-only
- only Qwen3 backbones are supported for now (also noted in docs)

* spec: fold DSpark into the DFlash arch

Address review: drop LLM_ARCH_DSPARK and the dspark.block_size /
markov_rank GGUF keys. A DSpark draft now converts to a DFlash GGUF;
the Markov head tensors are detected by presence (like eagle3 d2t),
block_size is read from the existing dflash.block_size key, and the
block anchors are taken as a strided view of the decoder's token
input instead of a separate graph input.

* spec: add confidence-based draft pruning for DSpark

The DSpark confidence head predicts per-position acceptance of the
drafted block. --spec-draft-conf-min truncates the block at the first
position below the threshold (default 0 = disabled).

* fold the dspark impl into dflash, selected by spec type

* address review comments

* dspark: clean up and improve naming

* update readme

* remove trailing whitespace

* dflash: draft full n_max blocks, defer dp.n_max to the central truncation

The DSpark markov head views the draft batch as a uniform [n_seqs x block]
grid, but the per-seq dp.n_max clamp could produce blocks of different
sizes, silently corrupting the strided views and the resulting logits.

Drop the clamp and always draft the full n_max block for every sequence:
dp.n_max is already enforced by the central truncation in
common_speculative_draft(), the same way eagle3 handles it.

Co-authored-by: Zaire404 <3147879462@qq.com>

* dflash: assert the markov head block-uniformity invariant, require the conf head

With the draft batch always submitting equal-size n_max blocks, a
non-divisible token count can only mean the batch was split across
ubatches or a caller broke the layout - fail loudly instead of silently
dropping the markov bias. The block_drafts > block_size early return
stays: worst-case graph reserve passes legitimately build with
n_seq_tokens > block_size.

Also make conf_proj required when the markov head is present: the
confidence head is part of the DSpark checkpoint format, and a missing
head would otherwise leave --spec-draft-conf-min silently reading stale
embeddings instead of confidences.

Co-authored-by: Zaire404 <3147879462@qq.com>

* dspark: fold conf_min into p_min

p_min and conf_min express the same thing - the minimum predicted
survival probability for a drafted position - differing only in how the
estimate is obtained: token probability for regular drafters, the
trained confidence head for DSpark. The DSpark readback never used
p_min, so reuse it for the confidence threshold and drop the separate
--spec-draft-conf-min flag. Both defaulted to 0 (disabled), so behavior
is unchanged.

Co-authored-by: Zaire404 <3147879462@qq.com>

* dflash: note the confidence broadcast workaround

Requested in review: the ggml_repeat only adapts the [1, n_tok]
confidences to the n_embd-wide embd_nextn transport so that
llama_get_embeddings_nextn can be reused - not a placeholder.

Co-authored-by: Zaire404 <3147879462@qq.com>

* cont : clarify

[no ci]

---------

Co-authored-by: Ruixiang Wang <wangruixiang07@outlook.com>
Co-authored-by: Zaire404 <3147879462@qq.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-07-28 14:43:27 +03:00
Ruixiang Wang a55a8c5266 convert : fix dflash target tokenizer mismatch during conversion (#25733)
* spec: fix dflash target tokenizer mismatch during conversion

* fix ci ty check
2026-07-16 15:19:47 +03:00
Thiago Padilha cb489bc0fb convert_hf_to_gguf: support split MTP export for HY V3 (#25641)
- Add a supports_mtp_export capability to ModelBase so architectures can opt
  into --mtp and --no-mtp without extending a central class allowlist.
- Enable the capability for the existing Qwen3.5/3.6 and Step3.5/3.7
  implementations, and for HY V3, whose converter already supports
  filtering the appended MTP layers.
2026-07-14 11:43:15 +02:00
Ruixiang Wang fa72bc6826 dflash: refactor draft model conversion (#25110)
* dflash: refactor draft model conversion

* apply fix for eagle3 convert
2026-06-28 20:31:48 +02:00
Ruixiang WangandKashif Rasul d1b34251bc spec : add DFlash support (#22105)
* spec: add DFlash v2 support

* dflash: support sliding window attention per layer_types

* docs: add dflash section

---------

Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
2026-06-28 16:01:34 +03:00
Sigbjørn Skjæret f4043fec01 convert : more consistent handling of rope_parameters (#24833) 2026-06-20 13:42:36 +03:00
Michael WandandSigbjørn Skjæret a4d2d4ae41 convert : add compressed-tensors NVFP4 support (#21095)
* Refactored Compressed Tensors NVFP4 support for new base.py

* Support compressed-tensors NVFP4 conversion

* Moved Qwen MTP remap into filter_tensors

* simplify

* pathlib no longer used

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2026-05-25 14:16:11 +02:00
IncarnasandSigbjørn Skjæret 1867a0c692 update bid to match each layers MTP source (#23237)
* update bid to match each layers MTP source

* Update conversion/qwen.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2026-05-18 12:37:12 +08:00
Aman GuptaandGeorgi Gerganov 255582687b llama + spec: MTP Support (#22673)
* spec: support MTP

* fix batch size

* rename files

* cont : simplify (#7)

* MTP: clean-up (#9)

* MTP: clean-up

* review: use llama_context_type instead of llama_graph_type

* review: remove llama_model_has_mtp

* review: fix convert issues

* convert: fix pycheck

* review: formatting

* use `mtp-` for identifying mtp models

* convert: fix mtp conversion

* mtp -> draft-mtp

* remove unused llama_arch

* add need_embd in speculative

* llama: allow partial seq_rm for GDN models for speculative decoding

Currently speculative checkpoint needs to restart from a checkpoint
after some draft tokens are not accepted, this leads to some wastage in
running the target again. This PR adds the ability to rollback upto
`draft_max` by storing the GDN intermediates.

* fix pending state

* vulkan: add GDN partial rollback

* meta: extend check to axis 1

* metal: add GDN partial rollback

Extend the gated delta net kernel to store intermediate states for
partial rollback support on the Metal backend.

- Add K (snapshot slot count) as a function constant
- Read input state from slot 0 of the 3D state tensor
- Write intermediate states to different slots during token loop
- For K=1, maintain backward-compatible single-slot behavior

Ref: https://github.com/ggml-org/llama.cpp/commit/8c05923630110223669f069af2000e9cf10c02bc

Assisted-by: llama.cpp:local pi

* delta_net_base: use ggml_pad instead of new_tensor

* review: add need_rs_seq

* review: rename part_bounded to n_rs

* review: deslop comments

* review: rename, add asserts

* server : adjust checkpoint logic (#11)

* server : adjust checkpoint logic

* cont : rm asserts

* server-context: fix early exit

* spec : fix compatibility with n-gram and add TODOs (#13)

* metal : cleanup

* llama : fix faulty bitwise check in recurrent memory

* server : disable RS-based MTP in combination with other spec types

* spec : add TODOs

* cont : fix comment

* cont : update comment

* common : fix logic for ngram + mtp compat

* llama-memory: enable checkpointing with partial rollback

* cont: add test-case for loading into a dirty ctx

* llama-memory-recurrent: clear rs_idx in clear

* download: fix mtp path

* llama-arch: fix enorm op

* docs: update docs

* conversion: fix type annotations

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-05-16 20:06:23 +08:00
Piotr Wilkin (ilintar)andSigbjørn Skjæret cc7200bf12 Refactor: convert_hf_to_gguf.py (#17114)
* move conversion code to a dedicated conversion directory and split the files akin to the src/models architecture

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2026-05-15 15:18:12 +02:00