Pascal [Mon, 16 Mar 2026 11:04:06 +0000 (12:04 +0100)]
Fix model selector locked to first loaded model with multiple models (#20580)
* webui: fix model selector being locked to first loaded model
When multiple models are loaded, the auto-select effect would re-fire
on every loadedModelIds change, overriding the user's manual model
selection. Guard with selectedModelId so auto-select only kicks in
when no model is chosen yet.
On AMD APU/iGPU devices (unified memory architecture), hipMemAdviseSetCoarseGrain
returns hipErrorInvalidValue because the hint is not applicable to UMA systems.
The previous CUDA_CHECK() call treated this as a fatal error, causing crashes on
APU systems such as AMD Strix Halo (gfx1151).
Fix: treat hipMemAdviseSetCoarseGrain as an optional performance hint - call it
without error checking and clear any resulting error with hipGetLastError().
Also add pre-allocation debug logging (GGML_LOG_DEBUG) to help diagnose memory
issues on APU systems, and store totalGlobalMem in device info.
Context: AMD APUs on Windows are affected by a ROCm runtime bug that limits
hipMallocManaged to ~64GB regardless of available system RAM. A fix has been
submitted upstream: https://github.com/ROCm/rocm-systems/pull/4077
Co-Authored-By: Claude Sonnet 4.6 <redacted>
* ggml/hip: remove unrelated changes, keep only hipMemAdviseSetCoarseGrain fix
---------
Co-authored-by: moonshadow-25 <redacted> Co-authored-by: Claude Sonnet 4.6 <redacted>
Max Krasnyansky [Sat, 14 Mar 2026 18:09:08 +0000 (11:09 -0700)]
hexagon: Q4_0 and MXFP4 repack fixes (#20527)
* hexagon: fix tail corruption with rows sizes not multiple of 256
* hexagon: use different stride for repacking partial blocks
* hex-mm: update repack and kernels to avoid shuffles for full 256-element blocks
Previous commit changed the repacking to use even:odd (0:1,2:3,..) packing
instead of the original (0:128,1:129,...) packing in order to fix tail corruption.
Since the mm kernels already deal with partial tails we can use even:odd
packing only for the last block.
This avoid performance penalty of having to shuffle to zip the elements
in the common case.
* hex-mm: update rmpy x8 for better optimizations
* hex-mm: tighten supported MUL_MAT checks to avoid spurios failures
Adrien Gallouët [Sat, 14 Mar 2026 09:06:14 +0000 (10:06 +0100)]
ggml : add native AVX512-FP16 support for F16 operations (#20529)
The overall benchmark speed remains almost the same because the CPU is
now calculating faster than the RAM can deliver the data. (See perf stat
results below showing 2.7 billion fewer instructions).
Also note that this path will be only enabled for native build or with
custom flags.
Zijun Yu [Sat, 14 Mar 2026 05:56:55 +0000 (13:56 +0800)]
ggml : add OpenVINO backend (#15307)
* Update build doc
* Add cgraph tensor output name to OV op name
* Update openvino build instructions
* Add initial NPU support
* draft NPU support version 2: prefill + kvcache
* NPU support version 2: prefill + kvcache
* Change due to ggml cgraph changes, not correct yet
* Change due to ggml cgraph changes, llama-3.2 CPU work
* Add AMD64 to CMakeLists
* Change due to ggml cgraph changes, all device work
* Refactor: clean, fix warning
* Update clang-format
* Statful transformation for CPU GPU
* Add SwiGLU
* Fuse to SDPA
* Replace Concat with Broadcast in MulMat for GQA
* Pull out indices creation for kv cache update
* Refactor: remove past_token_len from extra_inputs
* Fix Phi3 SwiGLU and SoftMax
* Pull out sin cos from rope
* Reduce memory: free ov weights node after graph conversion
* Fix CPY due to cgraph change
* Added OpenVINO CI/CD. Updated docs
* Fix llama-cli
* Fix Phi3 ROPE; Add test-backend-ops
* Fix NPU
* Fix llama-bench; Clang-format
* Fix llama-perplexity
* temp. changes for mark decomp
* matmul in fp32
* mulmat input conversion fix
* mulmat type conversion update
* add mark decomp pass
* Revert changes in fuse_to_sdpa
* Update build.md
* Fix test-backend-ops
* Skip test-thread-safety; Run ctest only in ci/run.sh
* Use CiD for NPU
* Optimize tensor conversion, improve TTFT
* Support op SET_ROWS
* Fix NPU
* Remove CPY
* Fix test-backend-ops
* Minor updates for raising PR
* Perf: RMS fused to OV internal RMS op
* Fix after rebasing
- Layout of cache k and cache v are unified: [seq, n_head, head_size]
- Add CPY and FLASH_ATTN_EXT, flash attn is not used yet
- Skip test-backend-ops due to flash attn test crash
- Add mutex around graph conversion to avoid test-thread-safety fali in the future
- Update NPU config
- Update GPU config to disable SDPA opt to make phi-3 run
* Change openvino device_type to GPU; Enable flash_attn
* Update supports_buft and supports_op for quantized models
* Add quant weight conversion functions from genai gguf reader
* Quant models run with accuracy issue
* Fix accuracy: disable cpu_repack
* Fix CI; Disable test-backend-ops
* Fix Q4_1
* Fix test-backend-ops: Treat quantized tensors as weights
* Replace get_output_tensor+memcpy with set_output_tensor
* NPU unify PD. Unify dynamic and static dims
* Clean placeholders in ggml-openvino.cpp
* NPU unify PD (handled internally)
* change graph to 4d, support multi sequences
* Fix llama-bench
* Fix NPU
* Update ggml-decoder.cpp
Hitting error while compiling on windows:
error C3861: 'unsetenv': identifier not found
Reason: unsetenv() is a POSIX function; it doesn’t exist on Windows. Visual Studio (MSVC) won’t recognize it.
Proposed fix: Use _putenv_s() (Windows equivalent)
This is supported by MSVC and achieves the same effect: it removes the environment variable from the process environment.
This keeps cross-platform compatibility.
* Update ggml-decoder.cpp
* Update ggml-decoder.cpp
* Update ggml-decoder.cpp
* Update ggml-decoder.cpp
* Update ggml-decoder.cpp
* Remove the second decoder for node. Moving the function into the model decoder
* Fix error for naive
* NPU prefill chunking
* NPU fix llama-bench
* fallback naive run with accuracy issue
* NPU support llma-perplexity -b 512 --no-warmup
* Refactor: split ov_graph_compute for dynamic and static
* remove unused API GgmlOvDecoder::get_output_stride(const std::string & name)
* minor update due to ov 2025.4
* remove unused API GgmlOvDecoder::get_output_names()
* remove unused API get_output_shape(const std::string & name)
* Modified API GgmlOvDecoder::get_output_type(const std::string & name)
* Removed API GgmlOvDecoder::get_output_op_params(const std::string & name)
* Removed API get_output_ggml_tensor(const std::string & name)
* Removed API m_outputs
* Removed m_output_names
* Removed API GgmlOvDecoder::get_input_names()
* Removed API GgmlOvDecoder::get_input_stride(const std::string& name)
* Removed API get_input_type
* Removed API get_input_type
* Removed API GgmlOvDecoder::get_input_shape(const std::string & name)
* Removed API GgmlOvDecoder::get_input_op_params(const std::string & name)
* Fix error for decoder cache
* Reuse cached decoder
* GPU remove Q6_K requantization
* NPU fix wrong model output shape
* NPU fix q4 perf regression
* Remove unused variable nodes
* Fix decoder can_reuse for llama-bench
* Update build.md for Windows
* backend buffer: allocate on host
* Use shared_buffer for GPU NPU; Refactor
* Add ov_backend_host_buffer; Use cached remote context
* Put kvcache on GPU
* Use ggml_aligned_malloc
* only use remote tensor for kvcache
* only use remote tensor for kvcache for GPU
* FIX: use remote tensor from singleton
* Update build.md to include OpenCL
* NPU always requant to q4_0_128
* Optimize symmetric quant weight extraction: use single zp
* Use Q8_0_C in token embd, lm_head, and for 5 and 6 bits quant
* Suppress logging and add error handling to allow test-backend-ops to complete
* Fix MUL_MAT with broadcast; Add unsupported MUL_MAT FLASH_ATTN cases
* Use bias instead of zp in test-backend-ops
* Update OV in CI, Add OV CI Tests in GH Actions
* Temp fix for multithreading bug
* Update OV CI, fix review suggestions.
* fix editorconfig-checker, update docs
* Fix tabs to spaces for editorconfig-checker
* fix editorconfig-checker
* Update docs
* updated model link to be GGUF model links
* Remove GGML_CPU_REPACK=OFF
* Skip permuted ADD and MUL
* Removed static variables from utils.cpp
* Removed initializing non-existing variable
* Remove unused structs
* Fix test-backend-ops for OV GPU
* unify api calling
* Update utils.cpp
* When the dim is dynamic, throw an error, need to is stastic forst
* Add interface compute_model_outputs(), which get the model output through computing the node use count & status in the cgraph to avoid the flag using
* No need to return
* Fix test-backend-ops for OV GPU LNL
* Fix test-thread-safety
* use the shape from infer request of output tensor create to avoid issue
* fix dynamic output shape issue
* fix issue for the unused node in tests
* Remove unused lock
* Add comment
* Update openvino docs
* update to OV release version 2026.0
* add ci ov-gpu self hosted runner
* fix editorconfig
* Fix perplexity
* Rewrite the model inputs finding mechanism (#54)
winogrande_score : tokenizing selected tasks
winogrande_score : calculating winogrande score over selected tasks.
split_equal: sequential split is not supported when there are coupled sequences in the input batch (you may need to use the -kvu flag)
decode: failed to find a memory slot for batch of size 46
failed to decode the batch, n_batch = 2048, ret = 1
winogrande_score: llama_decode() failed
same for hellaswag:
split_equal: sequential split is not supported when there are coupled sequences in the input batch (you may need to use the -kvu flag)
decode: failed to find a memory slot for batch of size 99
failed to decode the batch, n_batch = 2048, ret = 1
hellaswag_score: llama_decode() failed
Georgi Gerganov [Fri, 13 Mar 2026 20:12:54 +0000 (22:12 +0200)]
graph : remove redundant GDN state transposes (#20443)
* 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 <redacted>
* 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 <redacted>
* llama : rever fgdn argument changes
* graph : remove GDN state transposes
* vulkan : adapt
* cuda : remove obsolete smem code
---------
Co-authored-by: Paul Flynn <redacted> Co-authored-by: Claude Opus 4.6 <redacted> Co-authored-by: Oliver Simons <redacted>
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.
SoftwareRenderer [Fri, 13 Mar 2026 17:58:09 +0000 (13:58 -0400)]
server: reset counter related to kill-switch on client error (#20513)
* server: reset kill-switch on client error
This avoids triggering a server kill switch.
If the client sends a request that exceeds the configured context size, an appropriate HTTP 400 response is provided and no tokens are generated.
However since no tokens are generated, update_slots() increments n_empty_consecutive. If the client sends 3 such messages in a row, the server terminates.
Daniel Bevenius [Fri, 13 Mar 2026 11:30:02 +0000 (12:30 +0100)]
mtmd : rename mtmd_get_audio_bitrate to mtmd_get_audio_sample_rate (#20105)
This commit renames the the function `mtmd_get_audio_bitrate` to
`mtmd_get_audio_sample_rate` to better reflect its purpose.
The motivation for this is that the function currently returns the audio
sample rate, not the bitrate (sample_rate × bit_depth × channels), and
that is how it is used in the code as well.
This is a breaking change, but I believe mtmd is still in
experimental/development phase so it might be alright to simply rename.
Daniel Bevenius [Fri, 13 Mar 2026 05:00:52 +0000 (06:00 +0100)]
convert : fix/suppress pyright errors (#20442)
* convert : fix/suppress pyright errors
This commit fixes the pyright errors that are generated by pyright for
convert_hf_to_gguf.py.
The motivation for this is that running this locally generates errors
that CI does not, and it can be difficult to spot new errors. One use
case is when working on new models which cannot be run in CI due to
privacy. Having the ability to run pyright locally is would be helpful
in this cases.
In the linked issue there is the mention of switching to `ty` which I
don't know anything about but in the meantime I would appreciate if we
could suppress these errors for now, and later perhaps revert this
commit.
With this change there are no errors but there are 4 informations
messages if the `mistral_common` package is installed. The
`--level error` flag can be used to suppress them.
ProgenyAlpha [Thu, 12 Mar 2026 10:32:04 +0000 (06:32 -0400)]
vulkan: add GATED_DELTA_NET op support (#20334)
* vulkan: add GATED_DELTA_NET op support
Implements the fused gated delta net recurrence as a Vulkan compute
shader with full support for scalar gate, KDA vector gate, GQA
broadcast, multi-token sequences, and permuted (non-contiguous) q/k
inputs. Specialization constants select head size (32/64/128) and
KDA mode at pipeline creation time.
Passes all 13 test-backend-ops cases on AMD Radeon 890M (RADV GFX1150).
Co-Authored-By: Claude Opus 4.6 <redacted>
* vulkan: optimize GATED_DELTA_NET shader (Phase 1)
- vec4 dot products on all inner loops (dp4 hardware intrinsic)
- Cache exp(g) in shared memory for KDA path, eliminating ~32K
redundant global reads and ~16K redundant exp() calls per token
- vec4 fused decay + rank-1 update (3 vec4 ops vs 12 scalar ops)
- Add perf benchmark cases for GATED_DELTA_NET to test-backend-ops
KDA TG: +5.4% throughput. Non-KDA: no regressions.
13/13 test-backend-ops passing on AMD Radeon 890M (RADV GFX1150).
Co-Authored-By: Claude Opus 4.6 <redacted>
* vulkan: address review feedback for GATED_DELTA_NET
ProgenyAlpha [Thu, 12 Mar 2026 09:03:18 +0000 (05:03 -0400)]
vulkan: fix SSM_CONV PP scaling with large ubatch sizes (#20379)
* vulkan: optimize SSM_CONV workgroup dispatch for large ubatch
Tile tokens into 2D workgroups (32x16) to reduce workgroup launch
overhead at large ubatch sizes. Add vec4 fast path for nc=4 (common
d_conv size). Fixes PP performance degradation with ubatch > 512.
Ref: ggml-org/llama.cpp#18725
Co-Authored-By: Claude Opus 4.6 <redacted>
* vulkan: remove unused shared memory declaration in SSM_CONV
Co-Authored-By: Claude Opus 4.6 <redacted>
---------
Co-authored-by: Progeny Alpha <redacted> Co-authored-by: Claude Opus 4.6 <redacted>
Georgi Gerganov [Wed, 11 Mar 2026 20:46:40 +0000 (22:46 +0200)]
llama : enable chunked fused GDN path (#20340)
* llama : enable chunked fused GDN path
* models : avoid Q and K repeats when using fused GDA
* cont : fix comment
Co-authored-by: Aman Gupta <redacted>
* cont : fix the fix
Co-authored-by: Aman Gupta <redacted>
* 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 <redacted>
* metal : validate contiguity of all input tensors in supports_op
Co-Authored-By: Claude Opus 4.6 <redacted>
* metal : add algorithm equivalence comment for GDA decay path
Co-Authored-By: Claude Opus 4.6 <redacted>
* cont : unslop + optimize
* cont : clean-up
---------
Co-authored-by: Paul Flynn <redacted> Co-authored-by: Claude Opus 4.6 <redacted>
* 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
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 <redacted>
* llama : refactor llm_build_delta_net_base API
---------
Co-authored-by: Aman Gupta <redacted> Co-authored-by: Paul Flynn <redacted> Co-authored-by: Claude Opus 4.6 <redacted> Co-authored-by: Oliver Simons <redacted> Co-authored-by: uvos <redacted>
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.
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.
- 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
* 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
overview / pkg / ggml / sources / llama.cpp / log