* models: use flash-linear-attention's l2norm for gated delta net q/k
The GDN q/k normalization is defined by flash-linear-attention as
l2norm(x) = x * rsqrt(sum(x*x) + eps)
with eps inside the root. Every GDN call site in the tree uses ggml_l2_norm
instead, which is x / max(sqrt(sum(x*x)), eps), i.e.
torch.nn.functional.normalize - its CUDA kernel cites that page.
The clamp never engages at these magnitudes, so in practice llama.cpp
normalizes with no epsilon at all where the reference has one inside the
root.
transformers made the same substitution when it first added Qwen3-Next and
corrected it three days later in huggingface/transformers#40842, 'Fix the
misalignment between the l2norm in GDN of Qwen3-Next and the implementation
in the FLA library'. vLLM and SGLang vendor FLA rather than reimplementing
it, so neither ever had the clamp.
eps keeps coming from the checkpoint, exactly as every call site already
passed it. The references hardcode 1e-6 for this norm; that is a separate
question and the two agree on every GDN checkpoint in the wild.
ggml_l2_norm itself is correct and unchanged, as is rwkv7-base, its original
caller, which passes normalize's own default eps of 1e-12.
No new ggml op: rms_norm already carries eps inside the root, so
rms_norm(x, eps/n) * (1/sqrt(n)) is exactly x * rsqrt(sum(x*x) + eps).
* Update src/models/models.h
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* 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 269a81e03d)
* 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 b1878a1017)
* 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 8f009f54be)
* 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 d1a592f278)
* 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 f824e09dc8)
* 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 189b67fc2c)
* 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 dbedc9e19c)
* 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.
* Fix input assignment in layer processing loop
Fix DFLASH for qwen-coder-next
* add line break
Added tensor for attention normalization in Qwen3 model.
* 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>
* ggml: backend-agnostic tensor parallelism
* support for GPT-OSS, Qwen 3 MoE
* partial Vulkan fix
* add support for 4/8 GPUs
* unconditional peer access
* re-use buffers + ggml contexts
* fix output pattern
* NCCL support
* GGML: HIP: add RCCL support
* Remove shfl and AllReduce from backend interface
* move allocation workaround out of ggml-alloc.c
* 2d tensor set/get support
* Fix the seg fault without NCCL
* Apply suggestion from JohannesGaessler
* support for tensor dims % n_devs != 0
* fix view_offs scaling
* arbitrary num. of GPUs/tensor split
* fix compilation
* better granularity estimate
* Support device-specific host buffer types if all underlying backends expose the same type. This allows using pinned memory instead of pageable memory for CUDA.
Fix compilation errors.
* partial Qwen 3 Next support
* Fix qwen3 30b (#8)
* Fix crash with Qwen-30B-A3B Q4_0
Qwen-30B-A3B Q4_0 has an intermediate dimension of 768. Using a granularity of 256 forces an uneven split between GPUs, which is not supported by the current implementation.
* Decide block size based on tensor quantization type
* Fix crashes due to KV cache serialization (#9)
KV cache serialization requires non-zero offsets on the tensor. Add support in the meta backend to set/get a tensor with a non-zero offset.
* metal : fix build (#7)
* static memory allocations, fix usage count
* fix tensor granularity
* more even memory distribution
* use BF16 for allreduce
* rebase fixup
* better error message for unsupported architectures
* Fix device mismatch during scatter of allReduce. (#11)
There is a mismatch between the dst buffer device and the backend device, causing the use of sync copies
* Enable the previous allreduce implementation. It is better in both perf and stability (#12)
* delay AllReduce for Moe for less I/O
* build : clean-up compile warnings
* backend : move most of the meta backend API to ggml-backend-impl.h
* cont : hide unused public API in the implementation
* llama : use llama_device + remove ggml_backend_dev_is_meta()
* ggml-backend : remove unused alloc include
* minor : remove regex include
* ggml : introduce ggml-ext.h for staging new APIs
* rebase fixup
* fix tests
* llama : more robust logic for determining Meta devices (#16)
* llama : more robust logic for determining Meta devices
* cont : fix devs size check
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* cont : fix log type
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
---------
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* disable roundtrip for meta backend
* fix arch selection
* Qwen 3.5 support
* fix Gemma 4 MoE
* fix OpenVino, SYCL
* fix test-llama-archs for CPU-only builds
* Fix Qwen 3.5 MoE
* disable meta backend tests for WebGPU
* tests : filter CPU-based devices from the Meta backend tests (#17)
* meta : formatting, naming, indentation (#18)
* formatting : llama-model.cpp
* formatting : ggml-ext.h
* formatting : ggml-backend-meta.cpp
* meta : add TODO
* add documentation
* better error messages
* fix GPT-OSS
---------
Co-authored-by: Carl Philipp Klemm <carl@uvos.xyz>
Co-authored-by: Gaurav Garg <gaugarg@nvidia.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Add control vector functions to qwen3.5 and qwen-next models
* Add missing cvec compatibility to the rest of the models
* Adjust comments and formatting
* cleanup
* whitespace
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* llama : enable chunked fused GDN path
* models : avoid Q and K repeats when using fused GDA
* cont : fix comment
Co-authored-by: Aman Gupta <amangupta052@gmail.com>
* cont : fix the fix
Co-authored-by: Aman Gupta <amangupta052@gmail.com>
* cont : fix
* metal : add GDN kernel (#20361)
* metal : add Metal backend for GGML_OP_GATED_DELTA_NET
Add a fused Metal kernel for the gated delta net recurrence op
(#19504), enabling GPU-accelerated inference for DeltaNet-based
models (Qwen3.5, etc.) on Apple Silicon.
Supports both GDA (scalar gate) and KDA (per-row gate) modes
with head_size 64 and 128. Unsupported configurations (head_size
32, non-contiguous tensors) gracefully fall back to CPU.
Performance: Qwen3.5-0.8B Q4_K_M on M4 Max
tg128: 170 -> 213 t/s (+25%)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* metal : validate contiguity of all input tensors in supports_op
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* metal : add algorithm equivalence comment for GDA decay path
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* cont : unslop + optimize
* cont : clean-up
---------
Co-authored-by: Paul Flynn <paul@arkavo.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* CUDA: AR gated delta net improvements (#20391)
* Add FastDiv to gated_delta_net_cuda
* Shard columns across warps
This reduces register pressure (avoids spill for S_v = 128) and gives
the warp-scheduler more CTAs to schedule (thus hiding data-access
latencies).
* Remove unneded include in gated_delta_net.cu
* Improve comments
* Apply code-formating
* Make sharding HIP-compatible
1. Use ggml_cuda_get_physical_warp_size() to determine warp size flexibly
2. Add test with partial warp to test sum reduction on CUDA
* Remove fastdiv_s64, as we can treat neqk1 and rq3 as uint32_t
* Rename variables
* Enable GDN also for prefill, move TODO for chunked_GDN
* Actually remove the TODO from 2068908975
* Get warp size at runtime
warp_size is not known at compile time in hip host code.
* Don't expose ggml_cuda_get_physical_warp_size on host
---------
Co-authored-by: uvos <devnull@uvos.xyz>
* llama : refactor llm_build_delta_net_base API
---------
Co-authored-by: Aman Gupta <amangupta052@gmail.com>
Co-authored-by: Paul Flynn <paul@arkavo.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Oliver Simons <osimons@nvidia.com>
Co-authored-by: uvos <devnull@uvos.xyz>
* models : add llm_build_delta_net_base
* cont : keep qwen35 and qwen35moe graphs intact
* cont : add comments [no ci]
* add kimi linear to delta-net-base
* removed unnecessary ggml_cont from g_exp_t
* removed ggml_cont from g_diff_exp_t. moved ggml_cont for o to kimi-linear.cpp
* removed unnecessary diag mask
* cont : simplify
* cont : avoid graph splits
* scale q after mul instead of beginning
* scale q after mul instead of beginning
* identical ppl
* cont : fix scale and decay mask
* minor : remove TODO
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Unified delta net handling
* Remove old methods.
* Refactor and optimize
* Adapt autoregressive version from @ymcki
* Change to decay mask approach
* Fix bad permute
* Qwen 3.5 support
* Apply suggestions from code review
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Further fixes
* Use inheritance, remove unneeded conts
* Not like this!
* Remove ggml.h explicit import
* Remove transformers, fix the views
* ACTUALLY fix views, make super calls explicit in conversion.
* Fix conversion again
* Remove extra ggml.h imports
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* qwen3next: simplify qkvz projection
* use ggml_swiglu_split
* revert swiglu_split, but remove redundant repeat()
* fix missing reshape
* rm 2 redundant transposes
* move mul_mat(k,q) to outside of chunking
* rm redundant cont
* improve g_cs_chunk
* add comments about no cont
* use std::pair instead of ggml_concat
* vectorize key_gdiff calculation
* rm unused tensor
* avoid ggml_concat inside loop
* bring back ggml_concat as it may not work on other backend
* nits
* It's Qwen3 Next, the lean mean token generation machine!
* Apply patches from thread
* Remove recurrent version, only keep chunked and autoregressive
* Remove unnecessary conts and asserts
* Remove more extra conts and asserts
* Cleanup masking
* Qwen3 Next - cleaned up version
* Whitespaces and stuff
* Correct minor errors
* Update src/llama-model.cpp
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Misc. fixes.
* Clean up code, add missing hybrid qualifier
* Did someone transpose the SOLVE_TRI result matrix? Perhaps...
* Whitespace
* Proper tensors for cb calls
* Use llama-graph.h vertical alignment
* BROKEN: chunking
* Set new tensors as inputs.
* Proper chunk logic
* It's the circle of life...
* More shenanigans for n_seq > 1
* Nail in the coffin?
* Fix Windows build
* Eh, one fails on Windows, the other fails on Mac... just use general capture.
* quant : cleanup
* model : cleanup
* qwen3 : cleanup
* cont : cleanup
* cont : cleanup
* ggml : revert change
* qwen3 : cleanup
* cont : cleanup
* Readd cmath
* qwen3 : fix typo
* Update convert_hf_to_gguf.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Usual suspects
* fix my bad suggestion
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
