Commit Graph
36 Commits
Author SHA1 Message Date
Georgi Gerganov ca8daad199 llama : drop the redundant cnv from llm_attn_mask (#31558)
The dspark block mask is now derived at input-fill time: llm_attn_mask::block_uniform
fills every token of a sequence with the mask row of its first token, so the
graph-level reshape/repeat in dflash is gone and cnv always aliases raw.

Assisted-by: dsh:llama.cpp/ggml-org/GLM-5.3-Flash-GGUF (Mac Studio, M5 Ultra, 256GB)
2026-11-03 08:11:06 +02:00
Aman Gupta 2cbca389f5 dflash: copy hidden features via device copies (#31506) 2026-11-03 09:02:32 +08:00
Aman GuptaandGeorgi Gerganov 1b6935b227 llama : flash_attn_ext_rows - more efficient unified kv for multi-seq (#29510)
* llama : use llm_attn_mask and kv_rows for unified attention

Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF (Mac Studio, M2 Ultra, 192GB)

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* cont : optimize `get_seq_cells`

* llama : build the kv_rows lists from per-sequence cell bitmaps

Keep a bitmap over the cells for each sequence (the transpose of `seq`), updated in seq_pos_inc/dec, and build the cell lists by walking its set bits. The lists stay in cell order, cells shared by several sequences go to every list, and nothing has to be rebuilt when cells are removed.

Also leave out of the lists the cells that the SWA hides from every token of the slice (standard and chunked SWA).

* cont : make get_kv_rows_p_min private

* cont : minor metal

* llama : use kv_rows for every ubatch of a unified cache

A ubatch made of equal-length runs with a single sequence each (f.ex. the drafts of several slots) now splits into per-sequence slices.

Any other ubatch (interleaved, uneven or coupled sequences) becomes a single slice over the cells of all its sequences instead of falling back to the dense KQ mask, so the graph keeps the topology of the reserved graph.

* llama : merge get_kv_rows_seq_ids and get_kv_rows_p_min into get_kv_rows_slices

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

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-11-02 18:13:33 +02:00
Anton IandPascal fb5997274e kv-cache : keep rotation constants on the GPU (#31073)
* kv-cache : keep rotation constants on the GPU

Assisted-by: Codex

* tests : verify resident KV rotation buffers

Assisted-by: Codex

* kv-cache : document remaining multi-device rotation work

Assisted-by: Codex

* kv-cache : support per-layer rotation buffers

Assisted-by: Codex

* kv-cache : fix hybrid SWA rotation inputs and mixed placement check

Assisted-by: Codex

* models : use per-layer rotation in mistral-large4 and dflash

* tests: drop the rotation buffer tests

---------

Co-authored-by: Pascal <admin@serveurperso.com>
2026-10-30 10:15:06 +02:00
Xuan-Son Nguyen 78feec062d model: mistral le chonk (#31376)
* llama: extend DSA and sdpark to new model

* fix ci
2026-10-29 15:43:33 +01:00
Georgi Gerganov 4b851fbee8 models : replace ggml_tensor** out-params with output structs (#31142)
The hyper-connection and DSA graph builders wrote their extra outputs
(post / comb gates, carried top-k selections, inject gates) through
ggml_tensor** out-params. Return them in a small struct next to the
primary output instead.

Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB)
2026-10-26 16:19:47 +02:00
Aman GuptaandGeorgi Gerganov a074215352 deepseekv4.1: follow-up review fixes (#31137)
* kv-cache : use ggml_backend_tensor_copy to refill the DSV4 K mirrors

* llama : move the Engram pad id to llama_hparams and the token map to llama_model

The saver no longer needs the deepseek41 model class.

* deepseek41 : drop the F32 src1 request on the HC mixes matmul

* ggml : add softplus TODOs in the backends that still use log(1 + exp(x))

* convert : make the DSV4/DSV4.1 modify_tensors generators, drop the redundant vision filter

* deepseek41 : clean up comments

* deepseek41 : drop the F32 src1 requests on the router and indexer matmuls

* convert : use format_tensor_name directly in DeepseekV4Model

* s/comp_kv_src/comp_il_src/g

* cont : fix TODOs for log1p

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-10-26 15:52:02 +08:00
Aman GuptaandDaniel Han 74bca39500 model: DSV4.1 flash (#31086)
* model : add DeepSeek-V4.1-Flash (deepseek41)

* deepseek41 : remove MXFP8, convert the Engram table to BF16

* deepseek41 : compute the compressed-KV read layers once in the cache

* deepseek41 : use get_cells() for the shared-history check, drop llama_kv_cache::seq_pos_tok_le

* deepseek41 : gather the Engram rows in-graph like qwen4exp, drop the host gather

* deepseek41 : keep the Engram hash constants in hparams.ple_*, one module per Engram layer

* deepseek41 : drop the LLAMA_DSV41_KV_MIRROR toggle

* deepseek41 : keep il last in build_hc_mixes

* deepseek41 : sort the top-k rows before the sparse gather

* tests : add deepseek41 to the Metal fusion baseline

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>
2026-10-25 09:43:51 +08:00
Hrishith Thadicherla 4912ac24f1 dflash : load optional FC input scale (#30945)
Assisted-by: Codex
2026-10-22 08:24:12 +03:00
Kartik Gulia cd0a5b6a18 models : add Nemotron Super 3.5 VL and Nemotron Bolt 74B A9B support (#30520)
* add support

* remove unneeded bos fix

* add video flag

* fix flake error

* remove video-specific budgeting

* convert : fix lilicorr-dflash bid clash

* spec : enforce lilicorr n_tokens condition

* spec : fix lilicorr walk

[no release]
2026-10-15 16:34:56 +03:00
Kartik GuliaandGeorgi Gerganov 843e7dcc15 spec : add lilicorr support (#30506)
* spec : add lilicorr support

* convert : use convention for hparam assignment

* add todo for hparam use in llama-batch.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* typo fix

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-10-15 05:49:25 +02:00
Pascal cb55ffe6e2 graph: skip the LM head for pooled embeddings (#30445)
* graph: skip the LM head for pooled embeddings

A context that extracts pooled embeddings outputs one vector per
sequence, but every model still expanded its LM head, so the graph
computed n_vocab logits per token and the context kept a host buffer
for them.

The models now only declare t_logits, and set_outputs() expands it
unless the context extracts embeddings with a pooling type other than
NONE. Since the toggle changes the graph shape for a pooled context,
set_embeddings() schedules a re-reserve in that case.

* graph: drop the redundant t_embd expand

Address review from @CISC: with embeddings on, build_pooling() already
expands its output for every pooling type, and a decoder graph without
embeddings does not read t_embd, so set_outputs() only expands
t_logits.

* graph: add build_logits() for the LM head output

Address review from @ggerganov: the LM head is expanded by a dedicated
build_logits(), called from llama_model::build_graph() like
build_pooling(), and set_outputs() only marks the outputs again.

* graph: call build_logits() before build_sampling()

Address review from @ggerganov: build_sampling() reads t_logits, so the
LM head is built first. A pooled context then skips the sampling layers
too, since it has no logits to sample from.

* nit
2026-10-13 16:16:14 +02:00
Muhammad SaadandSigbjørn Skjæret 071b553fb1 models : remove redundant ggml_cont calls now supported by all unary kernels (#30198)
* models: remove redundant ggml_cont calls now supported by CUDA unary kernels

* models: restore cont_2d after sigmoid for broadcast mul, clean dflash cont

* Update src/models/qwen3next.cpp

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

* models: restore cont_2d before sigmoid in qwen3next

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
2026-10-13 09:26:52 +02:00
Hrishith Thadicherla a11f57ba93 model : fix DFlash output head sharing (#30111)
* llama : fix DFlash output head sharing

Assisted-by: Codex

* dflash : read tied output weights from GGUF metadata

Assisted-by: Codex

* llama : share tied word embedding metadata

Assisted-by: Codex

* llama : remove DFlash embedding head fallback

Assisted-by: Codex
2026-10-08 17:42:28 +02:00
Xuan-Son Nguyen 0bb496dbd3 llama: support both embd + raw tokens in batch (#29622)
* llama: support both embd + raw tokens in batch

* add to test-llama-archs

* also check case llm_arch_supports_mixed_batch = false

* constant graph topology

* have dedicated input for mixed case

* rm set_tensor_backend

* is_embd --> type

* consolidate m-rope pos handling into one place

* nits
2026-10-05 01:35:49 +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
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
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
Chris Peterson 9e71716247 models : move build_arch_graph() after graph() template specialization (#28934)
Move build_arch_graph()'s function definitions after the graph<true>
and graph<false> template specializations have been explicitly defined.
2026-09-15 12:33:26 +03:00
Yaniss Amazouz c61b98b875 model: add NVIDIA Nemotron-3-Puzzle-75B-A9B (NemotronHPuzzle) support (#25444)
* hparams: add per-layer n_ff_exp/n_expert_used arrays with scalar-or-array loading

G1/G2 infrastructure for variable-per-layer expert FFN size and top-k routing
(required for Puzzle-75B which has 5 distinct n_ff_exp values and 7 top-k values
across its 40 MoE layers).

Design: rename scalar members to _impl suffix (following existing convention),
add LLAMA_MAX_LAYERS arrays, add n_ff_exp(il)/n_expert_used(il) accessors with
scalar fallback. No new GGUF keys: reuses existing expert_feed_forward_length and
expert_used_count keys via get_key_or_arr (scalar -> broadcast, array -> per-layer).

- llama-hparams.h: n_ff_exp -> n_ff_exp_impl, n_expert_used -> n_expert_used_impl;
  add n_ff_exp_arr / n_expert_used_arr arrays; add per-layer accessor declarations.
- llama-hparams.cpp: implement n_ff_exp(il) and n_expert_used(il); out-of-range
  il returns impl safely (shared code, no abort).
- llama-model.cpp: central n_expert_used load changed to get_key_or_arr; derive
  impl as max-of-array for validations and backward compat; zero both new arrays;
  HunyuanVL override also zeroes n_expert_used_arr.
- llama-graph.cpp: aggregation loop in build_moe_ffn uses hparams.n_expert_used(il)
  so per-layer top-k bounds the ggml_view loop correctly.
- All other files: mechanical rename hparams.n_{ff_exp,expert_used} -> *_impl.
  Scalar arches are unaffected (broadcast fills all array slots with the single value).

(cherry picked from commit 269a81e03d66e1c353e1a203a0c03a03eb2b1a4e)

* nemotron-h: use per-layer n_ff_exp(il) and n_expert_used(il) at MoE call-sites

Load n_ff_exp via get_key_or_arr into hparams.n_ff_exp_arr in load_arch_hparams;
derive impl as max for existing uniform GGUFs.

In load_arch_tensors, compute n_ff_exp_i = hparams.n_ff_exp(i) with fallback to
n_ff(i)/n_expert_used(i) for GGUFs that omit expert_feed_forward_length.

In build_ffn_layer, pass hparams.n_expert_used(il) to build_moe_ffn so per-layer
top-k is used for expert routing selection.

All other nemotron-h behaviour (mamba2, attention, shared-exp, latent projection,
routed_scaling_factor, expert_weights_norm, sigmoid gating) is unchanged.

(cherry picked from commit b1878a101793cd4e59868ac72635a86ea694987c)

* arch/*.cpp + gguf-py: mechanical rename n_ff_exp->n_ff_exp_impl, n_expert_used->n_expert_used_impl

All non-nemotron arch files continue using the scalar impl member directly.
Behaviour is identical: the impl value is the broadcast value from the GGUF scalar.

gguf_writer: add_expert_feed_forward_length and add_expert_used_count now accept
int | Sequence[int], mirroring add_feed_forward_length, so converters can write
per-layer arrays with the same existing GGUF keys.

(cherry picked from commit 8f009f54bea5ef9a6a354123bd25e9d5ea2d5e03)

* convert: support NemotronHPuzzleForCausalLM (per-block MoE config)

Parse block_configs/mtp_block_configs into per-layer arrays (scalar-or-array
keys), append the MTP [attention, moe] sub-blocks as blk.88/blk.89 with
nextn tensors, accept the backbone.* prefix, and register the arch.
Also fix a pre-existing undeclared _experts attribute on NemotronHModel.

(cherry picked from commit d1a592f278336e78457454eb6c96bca917135f10)

* nemotron-h: distinguish Nemotron 3 Puzzle (75B.A9B) from Super (120B.A12B)

Both have 88 layers; the per-layer expert_used_count array (heterogeneous
for Puzzle, broadcast-uniform for Super) is the discriminator.

(cherry picked from commit f824e09dc812169589cf5662c92d149a4c18c30a)

* convert: accept the official Puzzle BF16 checkpoint's tensor naming

The officially distributed BF16 checkpoint (NVIDIA-Nemotron-Labs-3-Puzzle-
75B-A9B-BF16) names the trunk model.* (model.layers.*, model.embeddings,
model.norm_f) where the original release used the NemotronH-style
backbone.*, and spells the router bias e_score_correction_bias instead of
e_score_correction.bias. Normalize both at the top of
NemotronHPuzzleModel.modify_tensors so either checkpoint converts; every
tensor name in the official index (42683 keys, MTP head included) resolves
through the tensor map after normalization.

(cherry picked from commit 189b67fc2c9d50970416c94b3317a6e7baa49b03)

* laguna: use n_ff_exp_impl for the uniform-MoE FFN size

Laguna landed after this branch was cut and reads hparams.n_ff_exp as a
scalar. This series turns it into a per-layer array with an n_ff_exp(il)
accessor, so the three scalar reads no longer compile. Laguna is a
uniform MoE, so point them at the scalar fallback n_ff_exp_impl, same as
deepseek2/qwen3moe/gemma4 in this series. No behaviour change.

(cherry picked from commit dbedc9e19c50dca0acdfb402362e2707bee424ae)

* arch: extend the n_ff_exp/n_expert_used rename to archs added upstream

kimi-k3, dflash, bailingmoe3, deepseek4, granite-swa and the nemotron-h MTP
block still referenced the scalar fields by their old names. n_ff_exp and
n_expert_used are accessors now, so those reads no longer compile; point the
non-per-layer archs at the _impl scalars and use the indexed form where the
call site is per-layer.

* convert: keep Puzzle opted out of the NemotronH MTP export path

#26725 added MTP export to NemotronHModel, keyed on num_nextn_predict_layers.
Puzzle's config carries that key, but NemotronHPuzzleModel bypasses
NemotronHModel.__init__ (its per-block config needs a different setup), so
_mtp_bid was never assigned and modify_tensors raised AttributeError on any
mtp.* tensor. Puzzle's head is also laid out by mtp_block_configs, not the
mtp.layers.* form the base maps.

Set _mtp_bid to None, drop mtp.* in filter_tensors, and declare
supports_mtp_export = False so --mtp / --no-mtp fail at the CLI.

* llama: replace n_ff_exp/n_expert_used scalars with per-layer accessors

Follow-up to review feedback: the previous revision kept the scalar
hparams fields alongside the new per-layer arrays, which duplicated
state that get_key_or_arr already handles by broadcasting a scalar
value over every layer.

Drop both scalars and expose n_ff_exp(il) / n_expert_used(il) built
exactly like the existing n_head_kv(il) and n_ff(il) accessors: they
index the array and GGML_ABORT out of range, with il defaulting to 0
so genuinely uniform call sites stay a plain n_ff_exp().

Arch loaders now read both keys through get_key_or_arr over
n_layer_all, and the n_expert_used validation checks the maximum
across layers instead of a single field.

* llama: restore per-key required flags on the expert hparam reads

The scalar-to-array conversion passed required=false at every call site,
which silently made mandatory keys optional. Each read now carries the
same required flag it had before the conversion.
2026-09-03 08:53:08 +02:00
662a0b0121 spec : fuse the DFlash encoder into the KV cache injection (#27310)
* dflash : fuse the encoder into the KV injection decode

The encoder is a single fc + norm, but running it as a separate
llama_encode forced a device-to-host round trip of its output before the
injection decode could re-upload it, plus a second graph build per
round. Fold the encoder into the decoder's embd branch and feed the
target features directly to one llama_decode.

Assisted-by: Claude Fable

* nit

* Apply batched suggestions from code review

Co-authored-by: Ruixiang Wang <wangruixiang07@outlook.com>

* Fix missing references from renaming

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
Co-authored-by: Ruixiang Wang <wangruixiang07@outlook.com>
2026-08-31 11:19:20 +02:00
JamePeng cc231cb0da dflash: pass missing NVFP4 scales to attention operations (#28000)
- DFlash2 NVFP4 draft models produced almost no accepted speculative
tokens because the Q, K, V, and output projection scales were not
passed to the corresponding graph operations.
2026-08-30 11:34:39 +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
Aman Gupta bf0a29cc16 Deepseek 4: -sm tensor (#26490)
* DSV4: sm tensor

* set coarser granularity for head splits

* fix dspark

* add model saving for dsv4 + allow dflash to return on specific device

* add comment about dsv4 seq_rm

* simplify

* add shared expert delayed allreduce

* remove special test for dsv4
2026-08-24 09:20:25 +03:00
Xuan-Son Nguyen 873e5d8e39 model: use ggml_rope_set_offset() (#27382)
* model: use ggml_rope_set_offset()

* partially apply to deepseek2
2026-08-21 18:54:29 +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 6fed9f6ff7 mtmd, common: various fixes (#27071)
* apply fixes

* cont

* revert gguf fix
2026-08-14 23:34:56 +02:00
Daniel Bevenius 2bacf9ea5c dflash : clarify output logging of target_layer_ids (#27013)
This commit tries to make the logging of target_layer_ids a bit clearer
and easier to read.

Currently the output generated looks like this:
```console
0.00.468.624 D load_arch_hparams: DFlash extract_layers = [0.00.468.626 D 2, 0.00.468.626 D 6, 0.00.468.626 D 20,
  0.00.468.626 D 30, 0.00.468.627 D 42, 0.00.468.627 D 520.00.468.627 D ]
```
With the changes in the commit the output will be:
```console
0.00.522.765 D load_arch_hparams: DFlash extract_layers = [2, 6, 20, 30, 42, 52]
```
2026-08-14 06:57:05 +02:00
Sigbjørn Skjæret ece98b87f7 model : disallow integer dflash sliding_window_pattern (#26900)
* fix sliding_window_pattern

* disallow integer pattern
2026-08-12 14:24:10 +03:00
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
Georgi Gerganov 1c3c9674de models : fix dflash wo_a reshape on load (#26577) 2026-08-04 16:56:49 +03:00
Aman Gupta 596a5795bd DeepseekV4 MTP + DSpark (#25784) 2026-08-02 20:55:34 +08:00
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 WangandGeorgi Gerganov 571d0d540d model: rotate injected K/V cache for DFlash (#25823)
* dflash: rotate injected K/V cache when using K/V quantization

* Update src/models/dflash.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* clearer format

* remove trailing whitespace

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-07-18 15:02:18 +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