* ggml : transpose fused GDN state access for coalesced memory reads (#20436)
The fused Gated Delta Net kernel accessed the [S_v, S_v] state matrix
column-wise on row-major storage, causing strided reads (stride S_v =
128 floats = 512 bytes) that waste GPU cache bandwidth. This produced a
39% regression on Qwen3.5-9B (Metal, M4 Max) compared to the unfused
path.
Transpose the state indexing so threads read contiguously:
- Metal: s_ptr[is*S_v] -> s_ptr[is] (stride 1 vs S_v)
- CUDA: curr_state[i*S_v+col] -> curr_state[col*S_v+i] (coalesced)
- CPU: restructured loops for row-wise transposed access
Also add --fused-gdn [on|off|auto] CLI flag (mirrors --flash-attn) so
users can control fused GDN independently of auto-detection.
All GATED_DELTA_NET backend-ops tests pass.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* ggml : use SIMD dot products in CPU GDN kernel, couple AR/chunked fused flags
- Replace scalar inner loops with ggml_vec_dot_f32 for SIMD-optimized
dot products in the CPU fused GDN kernel (delta and attention output)
- Couple fused_gdn_ar and fused_gdn_ch flags in auto-detection: if one
path lacks device support, disable both to prevent state layout mismatch
between transposed (fused) and non-transposed (unfused) formats
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* llama : rever fgdn argument changes
* graph : remove GDN state transposes
* vulkan : adapt
* cuda : remove obsolete smem code
---------
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>
* llama : fix pooling assertion crash in chunked GDN detection path
The chunked fused Gated Delta Net detection in sched_reserve() calls
graph_reserve(16*n_seqs, n_seqs, n_outputs, ...) where n_outputs = n_seqs.
This creates a dimension mismatch in build_pooling() for embedding models
with mean/rank pooling: build_inp_mean() creates a tensor with shape
[n_tokens=16*n_seqs, ...] while t_embd is reduced to [n_outputs=n_seqs, ...]
via out_ids, causing ggml_mul_mat to assert on ggml_can_mul_mat(a, b).
Fix: pass n_tokens as n_outputs in the chunked GDN graph reservation,
matching the pattern used by the pp/tg worst-case reservations.
Regression introduced by #20340 (d28961d).
Same class of bug as #12517, fixed by #12545.
* server : add mean pooling tests to embedding test suite
Add test_embedding_pooling_mean and test_embedding_pooling_mean_multiple
to cover the --pooling mean codepath, which was previously untested.
These tests would have caught the regression introduced by #20340 where
build_pooling() crashes with a ggml_mul_mat assertion due to mismatched
dimensions in the chunked GDN detection path.
---------
Co-authored-by: Domenico Crupi <domenico@zerovolt.it>
* tests: allow loading test-backend-ops tests from json
* add error threshold based on op
* add error when file cannot be read
* add graph operator json extraction tool
* add nb parameter for non-contiguous input tensors
* fix view check
* only use view if non-contiguous/permuted, use C++ random instead of rand()
* replace internal API calls with public llama_graph_reserve call
* reduce test description length
* fix nb[0] not getting set for view
* add name to tests
* fix inplace error
* use text file instead of json
* move llama_graph_reserve function to new llama-ext header, move export-graph-ops to tests/
* fix missing declaration
* use pragma once
* fix indent
* fix Windows build
* 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>
* WIP: add NVFP4 quantization support
* tests
* improve NVFP4 dot product implementation performance and fix bad super call
* typo
* Use nvfp4 kvalues
* vulkan : fix NVFP4 shader compilation by including kvalues_mxfp4 lookup table
* vulcal and perf fixes
* wip
* Fix metal
* fix vulcan
* Rename threshold & fix wrong scale
* Fix MOE
* Shelf backend implementations (CUDA, Metal, Vulkan, arch-specific SIMD)
Remove NVFP4 support from GPU backends and architecture-specific
optimized dot products. These should be added in separate PRs so
backend specialists can review them independently.
Reverted files:
- ggml-cuda: common.cuh, convert.cu, mmq.cu/cuh, mmvq.cu, vecdotq.cuh,
quantize.cu/cuh, mma.cuh, ggml-cuda.cu, fattn-tile.cuh
- ggml-metal: ggml-metal.metal, ggml-metal-device.cpp, ggml-metal-impl.h,
ggml-metal-ops.cpp
- ggml-vulkan: ggml-vulkan.cpp, all vulkan-shaders/*
- ggml-cpu arch: arm/quants.c, x86/quants.c, powerpc/quants.c, s390/quants.c
Core NVFP4 support (type definition, CPU fallback dot product,
quantization, dequantization, conversion) is retained.
* Fix arch-fallback.h: add NVFP4 generic fallback for all platforms
After shelving backend-specific SIMD implementations, the generic
CPU dot product needs to be aliased on ARM, x86, PowerPC, and s390
platforms that previously relied on arch-specific versions.
* quantize: add NVFP4 as a quantization type option
* Fix ggml_fp32_to_ue4m3: handle subnormal values
Previously, values with ue4m3_exp <= 0 were clamped to 0, causing
all small scales to underflow. This made NVFP4 quantization via
llama-quantize produce garbage (PPL = 5.8M) since typical transformer
weights have amax/6.0 in the range 0.001-0.01, which falls in the
UE4M3 subnormal range.
Now subnormals are properly encoded as man * 2^-9 (exp=0, man=1..7),
matching the decode path in ggml_ue4m3_to_fp32.
Result: NVFP4 requantization now produces PPL = 15.25 (vs F16 = 14.33),
comparable to Q4_1 (PPL = 15.81) at slightly lower BPW (4.70 vs 5.15).
* Restore ARM NEON NVFP4 dot product implementation
Restores the optimized ggml_vec_dot_nvfp4_q8_0 for ARM NEON using
vqtbl1q_s8 lookup and ggml_vdotq_s32 dot products.
tg128 performance: 4.37 t/s (generic) -> 13.66 t/s (NEON) = 3.1x speedup
* Optimize ARM NEON NVFP4 dot product: LUT + vpaddq + vfmaq
- Add ue4m3_scale_lut[128] to ggml-common.h replacing branch-heavy
ggml_ue4m3_to_fp32() in the hot loop
- Use vpaddq_s32 for pairwise int32 reduction instead of vaddvq_s32
- Accumulate with vfmaq_f32 into float32x4_t vector accumulators
tg128: 8.1 -> 31.0 t/s (3.8x speedup, 77% of Q4_1 speed)
* ARM NEON NVFP4: rearrange q8 to match nibble layout
Alternative approach: rearrange q8 data to match the NVFP4 lo/hi
nibble layout instead of rearranging the looked-up NVFP4 values.
Eliminates vcombine_s8(vget_low, vget_low) shuffles.
Performance is equivalent (~18.5 t/s) - the bottleneck is the 2x
block overhead from QK=16 vs QK=32, not the shuffle instructions.
* CPU only backend 64 super-block layout
* cleanup
* Remove unused LUT
* int
* exclude NVFP4 from unsupported ops in metal build
* remove quantization for now
* store scales as native UE4M3, preserve original model bits when possible
* Update convert_hf_to_gguf.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* correct comment
* format
* reduce duplication and cleanup
* Address comments
* move detection to prepare_tensors
* Use math instead of const
* Move
* fix comment
* Shelf quantize tests
* Rebase and move check
* cleanup
* lint
* Update gguf-py/gguf/scripts/gguf_convert_endian.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Use fallback quant config
* Simplify
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* organize
* Refactor
* Update convert_hf_to_gguf.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Update convert_hf_to_gguf.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Update convert_hf_to_gguf.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* add quantize_nvfp4 (required for test_quants.py)
* add quantize_nvfp4 (required for test_quants.py)
* add quantize_nvfp4 (required for test_quants.py)
* fix return type
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* llama : add support for Nemotron 3 Super
This commit adds support for the Nemotron 3 Super model (120B.A12B)
enabling this model to be converted to GGUF format and run in llama.cpp.
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Matt Clayton <156335168+mattjcly@users.noreply.github.com>
* llama-quant : correct `n_attention_wv` usage
In #19770, I introduced a regression in the way the
`quantize_state_impl` counter values were initialized. I was
incrementing and using `n_attention_wv` in the same loop, when it should
have been fixed by the time we're deciding tensor types in
`llama_tensor_get_type_impl` (for `use_more_bits`).
I never observed a difference in any of [my
tests](https://github.com/ggml-org/llama.cpp/pull/19770#issuecomment-4000424712)
- it was only after @bartowski kindly pointed this out that I realized
it was incorrect. (Thanks!)
* simplify
* quantize : imatrix-fail early + code cleanup
* fix manual override printing
it's in the preliminary loop now, so needs to be on its own line
* revert header changes per ggerganov
* remove old #includes
* clarify naming
rename `tensor_quantization` to `tensor_typo_option` to descirbe its
functionality
* fix per barto
* tests: add end-to-end tests per model architecture
* fixup for rebase
* fix use-after-free in llama-model-loader.cpp
* fix CI
* fix WebGPU
* fix CI
* disable CI for macOS-latest-cmake-arm64
* use expert_weights_scale only if != 0.0f
* comments
* 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
* block implementation for kda
* remove space at the end of line 101
* concat+pad
* pad+binary row concat
* chunk size 16 for kda
* removed minor differences to master
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* model : fix Qwen3.5 model type detection
* Update src/llama-model.cpp
whoops, my bad
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Many models have vocabulary sizes, and thus tensor shapes, with more
than 5 digits (ex: Gemma 3's vocab size is 262,208).
I already fixed this for `llama_format_tensor_shape` but missed it for
`llama_format_tensor_shape` until now. Oops.
* WIP: Add EuroBERT support with autoformatting changes
This commit includes:
- EuroBERT model implementation for GGUF conversion
- C++ backend support for EuroBERT architecture
- Unintended autoformatting changes to Python files
Saving before reverting formatting-only changes.
* feat: add back eos assert when not last token pooling
* feat: removed duplicated code and cleanup
* feat: removed not working architectures and unnecessary check
* fix: typo
* fix: dynamic pooling config
* feat: added an example model for eurobert
* feat: proper llama-vocab implementation for jina-v5
* fix: removed unnecessary comments
Colin Kealty
Sigbjørn Skjæret
Georgi Gerganov
sprayandwipe
Michael Wand
ZeroV0LT
Ruben Ortlam
Asbjørn Olling
Richard Davison
Daniel Bevenius
Vinicios Lugli
ddh0
ddh0
Xuan-Son Nguyen
Johannes Gäßler
Aman Gupta
Tim Neumann
ymcki
Eric Zhang
Marcel Petrick
Maximilian Werk