* support cuda virtual devices
* disable NCCL path when virtual devices are used
* label virtual devices in description; add GPUx2 server CI jobs
* code refactor
PR #16308 set info.devices[id].integrated = false unconditionally for all
CUDA/HIP devices as a workaround for corrupted output on Jetson Orin
(#15034). On HIP/ROCm the device's real hipDeviceProp_t.integrated flag is
needed: with the cached field forced to false, supports_buft() refuses
CUDA host buffers on AMD APU/UMA parts, while get_type() already reads
prop.integrated (#23007) — an inconsistency that breaks integrated-GPU
host-buffer use on ROCm.
Guard the workaround so it only applies to non-HIP (CUDA) builds and
restore prop.integrated for HIP, keeping the Jetson workaround intact for
CUDA.
Fixes#23977
Signed-off-by: liminfei-amd <91481003+liminfei-amd@users.noreply.github.com>
* CUDA: dedup MoE gate/up activation quantization (fp4)
For MoE gate/up projections the src1 activation is broadcast across the
routed experts (ne11 == 1), so ids_src1 maps every one of a token's
n_expert_used slots to the same physical row. The MMQ path therefore
re-quantized each token's activation n_expert_used times.
For fp4 (NVFP4/MXFP4) src0, quantize each unique token row once instead of
once per expert. For NVFP4 a single quantize+scatter kernel
(quantize_scatter_mmq_nvfp4) quantizes each token once and writes the
resulting block_fp4_mmq straight to all n_expert_used slots, using an
inverse token->compact-row map (build_tok2c). MXFP4, and
GGML_CUDA_MOE_QUANT_GATHER=1, use a two-kernel variant: quantize unique
rows then gather into the expert-sorted layout (gather_mmq_fp4_blocks).
Both are bit-identical to the previous gather-then-quantize path (identical
source data, deterministic per-block quantization), verified by
test-backend-ops MUL_MAT_ID (type_a=nvfp4, broadcast b=1; 790/790 for the
default, gather, and per-expert paths) and by coherent end-to-end
generation. Set GGML_CUDA_NO_MOE_QUANT_DEDUP=1 to force the original
per-expert path.
Same-binary A/B on RTX 5090 (sm_120), Qwen3.6-35B-A3B-NVFP4 prefill @8192
(nsys, graphs-off; the unchanged mul_mat_q GEMM confirms stable clocks):
activation-quant GPU-busy drops 61% (78.2 -> 30.4 ms) with the fused
quantize+scatter, vs 33% (78.2 -> 52.8 ms) for the two-kernel gather. The
fused path avoids materializing and re-reading the 8x compact buffer,
writing the expert copies directly from registers.
* CUDA: bounds-check token ids in build_tok2c_kernel
Guard against malformed ids_src1: skip out-of-range token ids (t < 0 or
t >= n_tokens) and drop entries beyond n_expert_used per token instead of
writing past the token's tok2c region. No behavior change for valid MoE
routing data; test-backend-ops MUL_MAT_ID 790/790.
* Refactor the code based on review comments
- Removed previously added kernels that were not necessary anymore\
- Added an inverse mapping from (token, slot) to compact row. Each token is quantized once and scattered to its compact rows.
* Adding q8_1 support for dedup and addressing review comments
* Add pragma unrolls
* Remove redundant cudaMemsetAsync call
* Removing follow up redundancies
---------
Co-authored-by: praneshgo <227579474+praneshgo@users.noreply.github.com>
* opencl: workaround for A850 compiler compat
* opencl: fix DX compiler version parsing and cleanup
---------
Co-authored-by: Li He <lih@qti.qualcomm.com>
* opencl: exclude Adreno A7x from using Adreno MoE kernels
Some compilers for A7x devices miscompile the repack kernels, corrupting
the weights and causing MoE models to generate garbage output
* opencl: exclude A6x and unknown Adreno from MoE weights repack
* cuda : CUDA GGML_OP_LIGHTNING_INDEXER implementation (generic vector kernel + wmma kernel)
* chore : remove indentation of #pragma unroll
* cuda : remove unnecessary kernel template declarations
* cuda : add WARPS_PER_BLOCK and K_VECS_PER_BLOCK template parameters in lightning indexer kernels to avoid duplication of constants.
* cuda : relax MMA architecture requirements to Turing in lightning indexer implementation
* chore : renamed variables
* chore : rename ggml_cuda_op_lightning_indexer() to ggml_cuda_lightning_indexer()
* chore : TODO for AMD rocWMMA
* chore : whitespace formatting
* chore : another variable rename to fix problems caused by shadowing
* chore : yet another rename, this time uppercased all constants
* cuda : added alignment checks for Q and K tensors in lightning indexer implementation
---------
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
* opencl: route `sub_group_shuffle_xor` to qcom ext when KHR ext is unavailable
KHR `sub_group_shuffle_xor` is not defined by compiler when
`cl_qcom_subgroup_shuffle` is present, causing certain FA
kernels fail to build. Define the KHR shuffle_xor using
the qcom extension.
* opencl: skip FA kernels with mixed and quant types for A7x to avoid compiler crash
* metal: fuse snake activation (mul, sin, sqr, mul, add)
Mirror the CUDA, Vulkan and CPU snake fusion: same matcher on the naive
5-op chain, same F32 contract on a and inv_b, same F32/F16/BF16 kernel
with F32 compute. Follows the Metal backend idioms: bf16 instantiation
gated behind GGML_METAL_HAS_BF16 and concurrency ranges checked on the
remaining chain nodes before encoding, as done by the bin fusion.
Covered by the existing backend-agnostic SNAKE_FUSE tests.
* metal: absorb snake fusion into ggml_metal_op_bin
Extract the matcher to ggml_metal_op_can_fuse_snake, mirroring the
Vulkan naming, and dispatch the fused path from ggml_metal_op_bin.
The encode loop switch is back to a single call per case.
Address review from ggerganov
* metal: fix indentation in ggml_metal_op_can_fuse_snake
Raise the threshold for minimum buffer size from 1 GiB to 4 GiB, based
on real-world experiments of overcommitting device memory with model
weights larger than available VRAM, for example Qwen3.5-35B-A3B-Q8
running on a B70.
Also add a debug message to better track USM system allocations.
Signed-off-by: Francois Dugast <francois.dugast@intel.com>
* [SYCL] F16 (default) Flash Attention with XMX engine via oneDNN graph API; Qwen3.6-27b-Q8_0 prefill speed up x1.21 at p=512 and x4.26 at p=80k
* [SYCL] Address review on FA oneDNN path. Result: llama-bench---pp512; 32% increase with fa1; llama-perplexity---0.11% difference; tested model: mradermacher/Meta-Llama-3.1-8B-Instruct-Q8_0.gguf
* PR-25222 revision v2: addressed audits
* [SYCL] flash-attn oneDNN SDPA KV F16 rev 3.0: add BMG gate + multi-device sync. Narrow the scrope of this PR to Battlemage only (bmg; Xe2). Other archs (e.g., alchemist) fall back to existing FA kernel. When device_count >1, apply stream -> wait_and_throw(), validated working path for multi-gpu sync fix by @maxious.
Co-authored-by: maxious <81432+maxious@users.noreply.github.com>
* updated comment on bmg gate, noted the issue
---------
Co-authored-by: scientist3 <scientist.3@users.noreply.github.com>
Co-authored-by: hmscider <hmscider@users.noreply.github.com>
Co-authored-by: maxious <81432+maxious@users.noreply.github.com>
The f16 GEMV kernels take a vectorized path for ne00 >= 128 that casts the row
pointers to half4 or float4. When the row stride is not aligned, the wide load
becomes misaligned. On devices that require natural alignment for vector loads,
the kernel reads garbage. This is the case Intel GPUs and the kernels produce
incorrect results there. Adreno happpens to be byte addressable and the kernels
happen to work.
* opencl: do not fail backend init on devices without cl_khr_integer_dot_product
* opencl: do not call dp4 kernels when dp is unavailable
---------
Co-authored-by: Li He <lih@qti.qualcomm.com>
* vulkan/cpu: Support f16 as SET_ROWS src.
This adds full support for f16 SET_ROWS (equivalent to f32) to vulkan and CPU
backends, and adds more backend tests.
* Set DenormPreserve 16 when supported, to try to fix failures on Intel
* tune error threshold
* update metal supports_op
* ggml: uniformize im2col dst_type for all conv ops
* Update ggml/src/ggml.c
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* ggml : uniformize im2col casting logic across all conv ops
* fix : allow im2col_f16 to accept any kernel type
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This uses the new VK_EXT_shader_ocp_microscaling_types extension to do fp4 type
promotions, and also uses the float8 extension to do ue4m3 promotions for
nvfp4. It's reasonable to assume that an implementation that supports fp4 will
also support fp8, so we don't need to handle all possible combinations of
support.
If a Cuda device has no or limited available memory, the actual call
to cudaMemGetInfo() itself can cause a fatal crash due to a cuda out
of memory error (there is not enough memory to actually query memory)
This causes an issue because we query memory for all devices at
startup even if the user isn't trying to use the device for inference.
Fix this by making the error non-fatal and assigning zero total/free
memory to the device. This will have the downstream effect of the fit
algorithm not trying to put any layers on it, which is desired outcome
vs hard crashing.
this also prevents crashes in cuda enabled builds when user explicitly
passes '-dev none'
* [Vulkan] Fixes llama-cli breaking over longer promts sizes
The llama-cli was breaking for longer promts sizes for q4_0 quantized networks. Causing due to insufficient shared memory.
* Removed the un-used Adreno device
* Updated matmul for small pipeline.
* hex-sort: add efficient bitomic sort in hvx regs up to 1024 elements
* hex-sort: fix inverted vrors
* hex-sort: specialize sort functions for the common cases
* hex-sort: add tracing and local context
* ggml : process data in smaller chunks in CUDA ggml_top_k() implementation to reduce temporary buffers memory usage
* ggml : allocate tmp_dst only only once before the loop
* chore : whitespaces
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* ggml : use chunked processing in both CUDA CUB top-k and argsort implementations
* chore : separate argsort_f32_i32_cuda_bitonic() call from return statement
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* chore : replace ternary operators with min/max
---------
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* metal : add CONV_2D_DW (depthwise 2D convolution) support
* test : add perf cases for CONV_2D_DW
* metal : use 3D dispatch for CONV_2D_DW kernel
* metal : add channel-tiled CONV_2D_DW kernel for non-contiguous layouts
* metal : simplify CONV_2D_DW dispatch and trim comments
* metal : merge duplicate CONV_2D_DW pipeline getters
* tests : add F16 CONV2D_DW tests
* cpu : fix F16 kernel support for CONV_2D_DW
* tests : remove commented-out CONV_2D_DW test block
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
CUDA is compiled with fast math and AMD/HIP is not — this flag lets AMD use fast math too.
We can't use -ffast-math: it implies -ffinite-math-only, which won't compile (ggml uses INFINITY for masking) and produces NaNs. -funsafe-math-optimizations gives the speedup without the NaN problems.
Co-authored-by: Mark Caldwell <mark@cloudhands.ai>
