* model: add NextN/MTP speculative decoding support for GLM_DSA (GLM-5.2)
Adds GLM-5.2 NextN/MTP as a --spec-type draft-mtp target: nextn tensor
loading via the qwen35moe/step35-style presence probe, a graph_mtp
builder (enorm/hnorm/eh_proj + dense MLA + sigmoid-gated MoE with
shared expert + shared head with fallbacks, _s scale tensors passed
for NVFP4), t_h_nextn extraction in the trunk graph, and MTP-context
KV setup: the draft head runs dense MLA, so the MTP context uses a
plain attention KV cache holding only the nextn layer(s) (same
pattern as the hybrid Qwen3.5 MTP context) while the main context
keeps the DSA cache, now filtered to trunk layers only.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* convert : support --mtp/--no-mtp export for GlmMoeDsaForCausalLM (GLM-5.2)
Opt GLM-5.2 into the supports_mtp_export contract (post-#25641 shape,
mirroring HYV3Model/Step35Model): --no-mtp drops the appended NextN
block (blk.78) and its nextn_predict_layers KV; --mtp keeps only the
NextN block plus shared embeddings/norm/lm_head. Default (bundled)
output is unchanged.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* 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>
* Add preliminary MiniMax-M3 support
Text-only port that re-uses existing components: MiniMax-M2 style GQA with
per-head QK-norm and partial rotary, DeepSeek-V3 style leading-dense and
routed/shared experts, and swigluoai activation. Sparse attention is not
yet supported (dense fallback); vision tower and MTP heads are dropped.
* MiniMax-M3 vision tower (mmproj + clip graph)
* Delete m3_vision_ref.py
* Update clip.cpp
* MSA
* Update constants.py
* Update minimax.py
* Cache creation. Working withotu flash attention
* Added flash attention for sparse layers
* Decomposed slow cpu OP into GPU + CPU ops. Massive speedup over long ctx
* Rewrote indexer op to be cuda native. Modified flash attention to match per group block picking
* Implement sparse attention calc out of stock ops.
* Fix a cache allocation and cont issue
* Fixed -fa auto crash, flagged debug spots
* Delete vocab.json
* Delete model.safetensors.index.json
* Delete generation_config.json
* Delete Minimax directory
* Handled multi stream case to fall back on Dense Attention
* Development scaffolding cleanup. No functional change to the decode or
4-way paths. Full debug harness remains at <8136a9c68ed7a5eb009aa67bba3fda8062f4648f> for reproducing the
selection-parity validation.
* Remove redundant comment from minimax-m3.cpp
* Changed 3 Gelu Ops for vision into Gelu_erf ops
* Assert that n_kv is multiple of 128
* Rename MSA index tensors to indexer convention
Note: All GGUFs generated before this change will need to be regenerated.
* Fix incorrect Assert
* Review driven changes (#3)
* Remove comment from conversion minimax.py
Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com>
* Remove whitespaces from constants.py
Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com>
* Tighten comment in minimax.py
Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com>
* inherit MiniMax-M3 from MiniMax-M2
* drop dead text_config fallbacks
* Add indexer writer methods
* Reuse LLM_FFN_SWIGLU_OAI_MOE
* Remove duplicate indexer setters, add only block_size/local_blocks, follow value naming convention
* Fix conversion error /gguf_writer.py
Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com>
* Update gguf-py/gguf/gguf_writer.py
Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com>
* Update gguf-py/gguf/tensor_mapping.py
Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com>
* Update conversion/minimax.py
Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com>
* Update conversion/minimax.py
Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com>
* Remove whitespace in src/llama-kv-cache.cpp
Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com>
* Remove Whitespace in Update src/llama-model.h
Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com>
* Remove whitespace in src/llama-hparams.h
Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com>
* remove multimodal code upon maintainer request. Will be made as a separate PR
* Whitespace clean in tensor_mapping.py
* Log cache size on launch, block ctx shift, support prompt caching
Log indexer cache size on launch
Disallow ctx shift
Support prompt caching
* Update minimax-m3.cpp
* Optimize implementation, add multi stream support.
Fully rewrote minimax-m3.cpp for speed and buffer size gains:
Unified the 4-way + decode, 1 FA call per layer instead of 4, with the groups mapped onto ne[3]
Custom CPU op now emits block-level mask, expanded on GPU, which causes CPU to GPU transfer to shrinks at prefill
Decode: ~25 nodes/layer vs ~50, no per-group concats/conts
Unified selection semantics, so both regimes rank bs + local bias (position-anchored local force), which means prefill/decode can no longer disagree on selection
can_reuse on the MSA bias input. Graph reuse at decode restored (was rebuilding the full graph every token)
In-place mask adds, shrinking compute buffer ~6.8 to ~4.2 GiB at ub2048/62k
Multi-stream: MSA now runs with -np N when kv_unified=false. Decode stays batched across streams (still 1 FA call), prefill loops per stream. dense fallback only for --kv-unified + multi-seq
Measured effect on expert offload bound setup: decode 6.2(4WAY)–7.15(MSA_decode) -> 7.7~7.8 t/s, flat from 5k to 60k+. prefill around 10% faster. buffer about 20% smaller, multi-user support.
* set default cache type to F32
* Fix potential DSA double indexer cache allocation bug, only allocate in-cache k_idx for archs that opt in
* remove F16 downcasts in MSA attention, force F32 indexer score accum
* Add Minimax eos to llama vocab
* Guard edge case where idx cache can become stale after a tail trim
* Update llama-kv-cache.h
* Update llama-kv-cache.cpp
* Update llama-kv-cache.cpp
* Update llama-kv-cache.h
* Update llama-kv-cache.cpp
* Review driven changes
* style fix
* indexer hparams are required
* fix tests
* fix lint
---------
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
* Start building graph - reuse deepseek32
* Enable kv cache and rotation for glm_dsa architecture
Just follow Deepseek 3.2 for now.
* Reuse prev_top_k for "shared" indexer layers
* GLM 5.2 uses LLAMA_ROPE_TYPE_NORM for the indexer.
This is transformers' `apply_rotary_pos_emb_interleave`
* Default indexer types to GLM pattern
Previous converted GGUFs like https://huggingface.co/unsloth/GLM-5.2-GGUF write indexer weights to _all_ layers, even if they are only required for "full" types. This PR relies on a new key "%s.attention.indexer.types"; if absent, it will use the default GLM 5.2 schedule as defined in https://huggingface.co/zai-org/GLM-5.2/blob/main/config.json#L26.
Note that conversion is not saving this key yet.
* Save indexer types to gguf, restore on load
* Use ggml_lightning_indexer when cparams.fused_lid
Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com>
* GLM 5 and 5.1 use full indexers
Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com>
* Fix indentation
* Ensure array is zero-filled
* Prefer explicit std::fill
* Assert prev_top_k exists for shared indexer
---------
Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com>
* model: add Hy3 (hy_v3) architecture support
Adds Tencent Hunyuan 3 (HF architecture HYV3ForCausalLM, GGUF arch
hy_v3): a MoE decoder stack with per-head Q/K RMSNorm, a sigmoid
router with expert selection bias, an always-active ungated shared
expert, and leading dense block(s) (first_k_dense_replace).
The base implementation is ported from charlie12345's fork
(https://github.com/charlie12345/ROCmFPX, src/models/hyv3.cpp),
adapted to current mainline APIs (hparams.n_layer(), build_qkv,
build_moe_ffn with fused gate_up + scale tensors, output_s).
Note: blk.N.exp_probs_b is stored without a .bias suffix for
compatibility with existing hy_v3 GGUFs produced by that fork.
Co-Authored-By: charlie12345 <charlie12345@users.noreply.github.com>
Co-authored-by: Piotr Wilkin <ilintar@gmail.com>
Assisted-by: Claude Fable 5
* llama : make all KQ masks (except the lightning indexer one) f16 if FA is used and remove zero attention bias in DeepSeek V4
* llama : remove dead code that repeats unified raw_k cache for each stream in DeepSeek V4 - no longer needed as raw_k is always non-unified.
---------
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
* Fix input assignment in layer processing loop
Fix DFLASH for qwen-coder-next
* add line break
Added tensor for attention normalization in Qwen3 model.
* convert: add dsv4 conversion
* add basic setup
* add llm_graph_input_dsv4
* add save-load state
* add sinkhorn eps - correction by @fairydreaming
* add rope fix
* cleanup dead code
* fix bugs
* support pro model: added by @fairydreaming
* remove redundant V cache
* Chat template
* remove debugging leftovers
* Add mechanism for inlining templates based on architecture
* s/deepseek-v4-flash/deepseek4/g
* s/deepseek-v4-flash/deepseek4/g continued
* enable graph reuse
* enable FA
* fix test llama archs
* rename
* compatibility with antirez ds4 GGUFs
* simplified set_gguf_parameters() by calling super class method, replaced moe.score_func with expert_gating_func.
* reserve worst-case kv-cache
* revert max split inputs
* address review comments
* add padding to enable FA
* pad only the final value of plan.n_kv to 256
* remove built-in cpp chat template
* cont: remove cpp built-in template
* rm outdated test
* replace ggml_view_3d() with ggml_reshape_3d()
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* only support n_seq=1 for now
* remove unused var
* cont: remove unused var
* use scale bias
* use correct ptr for can_reuse
* remove gen-chat-inline-templates.py
* simplify graph reuse
* cont: cleanup
* remove unused inputs
* enable partial checkpointing
* add correct shape for kq_mask + set llama_model_n_swa to 0 for dsv4
* precompute source_idx + add comment about dummy write
* support multi-seq
* remove restored_trim_pos
* use split_equal when possible
* fix indent
* address review comments
* use LLM_KV
* fix ci
---------
Co-authored-by: Piotr Wilkin <piotr.wilkin@syndatis.com>
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
GLM-5.2 ships the DSA "lightning indexer" on only a subset of layers (the
"full" layers; others omit it), but the GLM_DSA loader created the five
indexer tensors on every layer as required, so loading any GLM-5.2 GGUF
failed with e.g. `missing tensor 'blk.3.indexer.k_norm.weight'`.
GLM_DSA's graph is llama_model_deepseek2::graph (plain MLA) and does not use
the indexer tensors (indexer runtime not yet implemented), so they are
loaded-but-unused. Marking them TENSOR_NOT_REQUIRED lets layers without an
indexer load as nullptr and the model runs as full MLA attention.
DeepSeek-V3.2 (uniform indexer on all layers) is unaffected.
* Add arch support for cohere2-MoE
* Removed redundant gating_func checks
* Changed ffn lookup to prefer prefix_dense_intermediate_size
* Renamed arch to cohere2moe
* Removed redundant lmhead check and chat template changes
* Removed lm_head.weight check from modify tensors, load output tensor not required, fallback to token_embd.weight
* Changed to (routed+shared)*0.5 for shared expert combined avg
* fixed sliding_window_pattern issue and pattern
* Fixed transformers crash 'first_k_dense_replace' error
* Remove comment
* Removed cohere2-moe as a tokenizer type and kept as tiny_aya. Renamed North-Mini-Code-1.0.
* Fixed MTP fail, changed to use iSWA
* Fixed remaining todos: cohere2moe renamed, changed swa parsing to use get_key_or_arr, removed extra get_arr use
* Force metadata usage
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Remove Cohere2 checkpoint comment
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Remove MTP comment
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Regenerate cohere2moe tokenizer hash
* Add cohere2moe to Llama Model Saver supported list
* Check for zerobios tensors and add support for Command to use LayerNorm
* Map expert_selection_fn to sigmoid in base.py instead of command.py
* use bools for foundnorm/foundnormrms
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Make ggml_gated_delta_net take only the initial recurrent state (D, 1, n_seqs) and passes the snapshot count K as an op parameter instead of inferring it from state->ne[1].
Remove the padding hack and copy all emitted snapshots into the recurrent cache with a single strided ggml_cpy
* Make GDN changes in all backends. Address review comments.
* Fix CI build errors
* feat(convert): Get language model conversion working for 4.1 vision
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat(convert): Skip multimodal tensors for GraniteMoeHybrid (vision 4.0)
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Disable vocab padding for non-hybrid models that use GraniteMoeHybrid
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Plumb python-side vision projector names and mappings
There are several awkward things here:
1. Most of these are essentially identical to the audio qformer tensors. On
the c++ side, that's mapped using the prefix, so the rest of the GGUF
name needs to align, but on the python side there's no prefix notion, so
they all get duplicated.
2. There are a couple of net-new tensors for vision, in particular
PROJ_NORM. In both speech and vision, the QF_PROJ_NORM is qualified as
belonging to the qformer portion, but the GGUF name is simply proj_norm
which conflicts with the ideal name for this new PROJ_NORM that is not
qualified as part of the qformer. To get around this, I used
"proj_layernorm" as the GGUF name.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add python side architecture name
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add python-side plumbing for setting FEATURE_LAYERS hparam
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add c++ side tensor naming defines
NOTE: Usage of these hasn't been updated to include prefix yet
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat(mtmd): Convert vision_feature_layer to an ordered vector
We need to preserve the ordering of these feature index values so that they
can be mapped to the sub-tensors within the stacked projectors.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat(mtmd): Add architecture label plumbing
Branch: Granite4Vision
AI-usage: full (OpenCode + qwen3.5:122b)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat(wip): Add partial conversion for mmproj
This handles stacking the projector tensors and setting the new harams
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add gguf_writer and constant support for new hparams and deepstack layer arr
Branch: Granite4Vision
AI-usage: draft (OpenCode + qwen3.5:122b)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Full conversion for mmproj w/ tensor mappings
Branch: Granite4Vision
AI-usage: full (OpenCode + qwen3.5:122b)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Add lm_head skip for mmproj for 4.0
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: De-alias text_config architecture in convert_lora_to_gguf.py
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add --trust-remote-code arg to convert_lora_to_gguf.py
This defaults to False, but allows a user to enable it programmaticly
instead of using the interactive prompt.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: De-alias model.language_model. -> model. for lora adapters
Branch: Granite4Vision
AI-usage: full (OpenCode + qwen3.5:122b)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Extend language model tensor dealiasing in adapters
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Remove unnecessary registration for GraniteSpeech in language model
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Plumb through mm prefix formatting for qformer tensors
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: Refactor vision projector tensors to use predictor ID as the block
This is cleaner than stacking them. The modeling file hard-codes
single-layer qformers, so we can punt on the multiipule multi-layer
projectors problem.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add spatial offests array hparam conversion
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add stub plumbing for granite vision in mtmd
Branch: Granite4Vision
AI-usage: draft (OpenCode + qwen3.5:122b)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add new hparam and tensor naming in clip-impl.h
New hparams:
- KEY_PROJ_SAMPLE_QUERY_SIDE
- KEY_PROJ_SAMPLE_WINDOW_SIDE
- KEY_PROJ_SPATIAL_OFFSETS
New tensors:
- TN_MULTI_PROJ_IMG_POS
- TN_MULTI_PROJ_QUERY
- TN_MULTI_PROJ_LAYERNORM
- TN_MULTI_PROJ_LINEAR
- TN_MULTI_PROJ_NORM
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Move deepstack_layer_arr to llm hparam instead of mmproj
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Remove IS_DEEPSTACK_LAYERS
This appears to have been added during Qwen3 VL
(https://github.com/ggml-org/llama.cpp/pull/16780), but it was never
actually used.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: n_deepstack_layers -> deepstack_layer_arr
The old logic hard coded a correspondence between the first N layers of the
LLM and the 1->N entries in the input embeddings. Now, that relationship is
maintained at loading time if the GGUF value is single-valued. If it is
multi-valued, it loads directly allowing for deepstack layers to be spaced
out throughout the model.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Use try/catch for single/multi valued deepstack info
The alternative would be to use get_key_or_arr, but then the single value
would be populated through the entire array and we'd need to detect that
and update it with the right correspondence.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add deepstack injection point for granite LLM
The use of ggml_add here assumes that the elements of inp_embd will be pre-
arranged to be the full embedding length with only the vision-mask'ed
portions non-zero from the projector. This matches how Qwen3VL does it.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: add missing vision attn layernorm eps
Branch: Granite4Vision
AI-usage: full (OpenCode + Qwen 3.6-35B)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: Hoist qformer tensors into qf_block and hold a vector for multi-proj
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Fix missing prefix template for TN_QF_PROJ_LINEAR
It's not strictly necessary since vision uses the blockwise version, but it
makes the loading consistent.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Add embedding scale and image grid pinpoints hparams in conversion
Also remove dead parsing for self._deepstack_layer_arr
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add mtmd KEY_ section for hparams shared with the LLM
In this case, we need the EMBEDDING_SCALE so we can unscale the image
embeddings to compensate for applying embedding scale to the input
embeddings
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Implement c++ hparam parsing
Branch: Granite4Vision
AI-usage: draft (Claude Code)
Co-authored-by: Eli Schwartz <eliyahu.schwartz@ibm.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Flatten pinpoints in conversion
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Add missing break
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: No reason to have modality prefix for img_pos
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add tensor loading
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix(convert): Fix confusion between proj.norm and proj.qformer.layernorm
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Use the right portion of speech for tensor loading!
Also plumb through the layernorm -> post_norm naming change
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add logging of deepstack_layers_arr if set
I also changed the print_f output type to int32_t to avoid printing
overflow values for -1. This could cause overflows on the other side, but
I can't imagine a value for any of the current array hparams that would
trigger that.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Make sure input embeddings are cont before f_embedding_scale
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add init and mmproj_embd cases for g4v
The n_mmproj_embd is 1+ to make space for the text embedding and all 8
projectors
Branch: Granite4Vision
AI-usage: draft (Bob)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Invert (h, w) -> (w, h) pinpoints
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Reorder projectors based on llm index and skip the first injection
The multi-projector stack has a strange asymmetry based on how it's
currently implemented for qwen3vl: on the mmproj side, it's all N
projectors, but the output of the "first" (by inp_embd index) projector is
automatically consumed as if it were a standard single-projector mmproj,
so the deepstack portion needs to only contain the 1-N entries.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Eli Schwartz <eliyahu.schwartz@ibm.com>
* fix: Fix mmproj hparams in conversion
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Eli Schwartz <eliyahu.schwartz@ibm.com>
* fix: Fix ordering/logic for deepstack injection in granite
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Eli Schwartz <eliyahu.schwartz@ibm.com>
* fix: Fix preprocessing config to match what the model needs
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Eli Schwartz <eliyahu.schwartz@ibm.com>
* wip: Partial port of Eli's implementation
This is still pretty broken, but it's getting closer. It now happily
generates tokens, but the values are quite incorrect still. I suspect it's
caused by the mapping of projectors from safetensors to their respective
orders here.
Also, this implementation breaks encapsulation pretty badly in mtmd_encode.
This will need a big refactor to put the G4V-specific encoding logic
somewhere more appropriate.
Branch: Granite4Vision
AI-usage: draft (Claude Code, Bob)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Eli Schwartz <eliyahu.schwartz@ibm.com>
* fix: Fix the pre-scaling on the input embeddings to correctly invert the scale
We've got tokens! They still don't line up quite right, so something's a
little off, but we're getting much closer now.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: invert embedding multiplier -> base_scale at load
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Fix setting image_resize_pad after new enum introduced
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Add G4V to mmproj mapping in conversion
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Re-add padding disable for non-hybrid hybrid models
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: Simplify G4V n_tokens computation
This is slightly more efficient and flexible for when we implement the
unpad cropping. IMO, it's also clearer that it is adding the number of
image_newline tokens (embeddings) to the grid, rather than recomputing the
entire count.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add new clip APIs for post-tile-encoding assembly
Granite 4 Vision uses llava-next style pack-and-unpad which requires
injecting the learned newline after each row of the tile grid. A row here
is a single row of the grid which is composed of (grid_x * cols_per_tile) *
(grid_y * rows_per_tile), so the result is newlines injected in between
individual tile rows, thus not something that can be handled with the
standard llava-uhd block-wise endcoding.
Branch: Granite4Vision
AI-usage: draft (Claude Code + Opus 4.7)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add model interfaces for granite 4 vision assembler
I'm on the fence about the best organization of this. These free functions
allow the per-architecture logic in clip.cpp to access the model-specific
graph building, but they still require a fair bit of model-specific logic
in clip.cpp which is not ideal.
I think a better approach may be to replicate what is done with the
graph builders themselves (and possibly even make the assembler part of the
model's existing graph builder).
Branch: Granite4Vision
AI-usage: full (Claude Code + Opus 4.7)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: Remove all g4v-specific branching from mtmd.cpp in favor of clip assembler
Branch: Granite4Vision
AI-usage: full (Claude Code + Opus 4.7)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor(mtmd): Consolidate assembler logic into clip_assembler class family
Just like `clip_graph` is the base class for building the model-specific
encoder graphs, `clip_assembler` will be the base class for building the
model-specific assembler graphs. This allows the assembly pattern to follow
how the encoder pattern is implemented where the model-specific logic lives
in a subclass co-located with the encoder graph builder that gets
constructed by a simple factory method.
Branch: Granite4Vision
AI-usage: full (Claude Code + Opus 4.7)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* style: Comment improvement
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: granite_vision -> granite4_vision
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Remove dead codepath for Qwen3VL add_vision_is_deepstack
These pieces were never used on the c++ side (removed there in an earlier
commit), so this is just cleanup that I missed before.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Oops! I did not mean to commit one of my prompt files
But now it's too far back in history to effectively rebase out, even with
interactive and --rebase-merges :(
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Add missing <algorithm> include for std::find
It seems that this was already pulled in on some platforms, but not on
others
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Fix Flake8 warnings in granite conversion module
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: Remove clip_assembler in favor of clip_image_f32.append_token
Per conversation in the PR, the clip_assembler pattern was too invasive.
This is a compromise that limits model-specific blocks to add_media where
each preprocessed tile is annotated with an injection type, after which all
the token counting logic is generic and the newline injection itself is
handled in the graph based on the value for the given tile image.
Branch: Granite4Vision
AI-usage: draft (Bob, OpenCode + Qwen 3.6 35b)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor(convert): Split n_deepstack_layers and deepstack_layers (array)
Branch: Granite4Vision
AI-usage: full (Bob, OpenCode + Qwen3.6-35b)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor(src): Handle n_deepstack_layers and deepstack_layers GGUF keys
Branch: Granite4Vision
AI-usage: draft (Bob, OpenCode + Qwen3.6-35b)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Fix GGUF key for deepstack_layers_arr
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: Remove pre-scaling embeddings and skip scaling for raw embd inputs
This follows how gemma3 and gemma4 handle embedding scaling by skipping the
multiplier for raw input embeddings.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: deepstack_layers(_arr) -> deepstack_mapping(_arr)
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: Fully revert changes to n_deepstack_layers and qwen3vl*
Since we're going to keep the GGUF KVs separate, it makes sense to just
keep the hparams separate too to limit the scope of this branch. The down
side is that n_deepstack_layers and deepstack_mapping_arr are potentially
conflicting.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Revert removal of "is_deepstack_layers" GGUF KV
This KV is not used at all on the c++ side, so it's fully dead, but there's
also no need to conflate this cleanup with the addition of G4V.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Remove unnecessary ggml_cont and build_forward_expand in cbx
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* style: Clean up comments
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Tighter and more flexible code for g4v_build_block
This could be refactored to look a lot more like granite-speech, but the
overall block constructs before/after the qformer are pretty different, so
for now I'm going to leave it as is and just tighten a bit.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Remove unnecessary `unordered_set` include
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Add architecture guard on deepstack_mapping_arr printout
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Remove unnecessary AI-gen comment
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Always initialize deepstack_mapping_arr with -1 values
This was causing `test-llama-archs` to fail, likely due to trying to save
the uninitialized values, then re-loading them. It's safer to always
initialize so that other models don't forget and end up with undefined
behavior.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* style: Remove TODO about block/vs non-block tensor mapping
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: Move is_vision_feature_layer logic into clip_hparams
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: Use a bool for append_token
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* style: Remove unnecessary comment
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Remove unused get_model api
yikes!
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: Rearrange helpers for g4v to be private members and use build_attn
Branch: Granite4Vision
AI-usage: full (Bob, OpenCode + Qwen3.6-35b)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Fix off-by-one in vision layer index
This was inherited from the Claude Code implementation that pushed the
negative index inversion down into the model file.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Fix norm/post_norm mixup in conversion
face. palm. :(
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* style: More descriptive tensor names
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Apply PR cleanup for new conversion changes
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* fix(convert): Remove duplicate V_ENC_EMBD_IMGNL
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: append_token -> add_newline
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* style: Comment cleanup
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Cleaner error handling/checking
NOTE: format_string is not available in granite.cpp (and including
clip-impl.h to get it doesn't compile, so I think it violates the intended
encapsulation), so std::stringstream is the simplest answer.
Branch: Granite4Vision
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
---------
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* Add support for the ibm-granite/granite-embedding-{97m,311m}-multilingual-r2 embedding models:
* Added a version of the gpt4o tokenizer that has a fixed regex (better handling of marks), and different token merging setting for the 97m model
* Reused gemma4 tokenizer for the 311m model
* granite-embedding-*-multilingual-r2 : add support SwiGLU FFN for Granite Embedding Multilingual R2
* added new GGUF key <arch>.hidden_activation (LLM_KV_HIDDEN_ACT) + writer
* added a forward declaration of llm_ffn_op_type to llama-hparams.h
* added llm_ffn_op in hparams
* added LLM_FFN_NONE = 0 sentinel to llm_ffn_op_type (value-initialization), modern-bert: explicitly assigns LLM_FFN_GEGLU before reading GGUF (unchanged).
* centralized hidden_act mapping in llama-model.cpp, added llm_ffn_op_type_from_string() helper, mirroring rope_scaling_type/llama_rope_scaling_type_from_string()
* modern-bert reads the GGUF key (when present) and uses the resulting op in its FFN graph
* Added granite-embedding-{97m,311m}-multilingual-r2 to the converter code
* Added the hashes for the granite embedding multilingual R2 models
* Set the hidden_activation in the GGUF if the field is present in config.json (such as for the granite embedding models)
* initial talkie support, coherent
* reorder to follow convention
* absorb inverse rope
* stop folding scalars to improve quantization
* use broadcasting instead of duplication
* style cleanup
* add scaling support to LoraTorchTensor; use that path in conversion
* use layer_out_scale instead of embd_skip_scale
