{"slug": "ggml-v1-0-0", "title": "Ggml v1.0.0", "summary": "Ggml released version 1.0.0, pruning its deprecated public API and removing the legacy DIAG_MASK_INF and DIAG_MASK_ZERO ops while bumping the RPC protocol to v9 to reject incompatible peers. The release adds configurable YaRN truncation via ggml_rope_set_truncate and ggml_rope_get_truncate, OCP FP8 support on CUDA, and backend performance work including few-row MMQ for batch sizes 2-24, a Vulkan prefill FlashAttention path, a device-side MoE scheduler on SYCL, and scheduler changes that skip uploading inputs that are not read. The API pruning and RPC protocol bump mean existing ggml-based integrations must update to remain compatible with peers running 1.0.0.", "body_md": "## Repository navigation\n\n## Overview\n\nggml 1.0.0 prunes the deprecated public API and the legacy `DIAG_MASK` ops, adds configurable YaRN truncation and FP8 support, and brings broad performance work across backends: few-row quantized matmuls and MoE fusion on CUDA/Metal, a Vulkan prefill FlashAttention path, a device-side MoE scheduler on SYCL, decomposed Adreno FlashAttention in OpenCL, new WebGPU kernels, expanded Hexagon op coverage, and scheduler improvements that avoid uploading unused inputs.\n\n### API changes\n\n- Pruned deprecated API and removed the legacy `DIAG_MASK_INF` /`DIAG_MASK_ZERO` ops, bumping the RPC protocol to reject incompatible peers ([llama/29801](https://github.com/ggml-org/llama.cpp/pull/29801) ,[llama/31946](https://github.com/ggml-org/llama.cpp/pull/31946) )\n- Added `ggml_rope_set_truncate` /`ggml_rope_get_truncate` to control YaRN correction-bound rounding ([llama/30206](https://github.com/ggml-org/llama.cpp/pull/30206) ,[llama/30802](https://github.com/ggml-org/llama.cpp/pull/30802) )\n- Implemented the backward pass for `TRI` ([llama/30712](https://github.com/ggml-org/llama.cpp/pull/30712) )\n- Added `MUL_MAT` src1 precision tests and gating for`ggml_prec_set_acc` ([llama/31896](https://github.com/ggml-org/llama.cpp/pull/31896) ,[llama/31851](https://github.com/ggml-org/llama.cpp/pull/31851) )\n- Bumped the RPC protocol to v9 with faster loading and graceful failure on unreachable endpoints or failed handshakes ([llama/29413](https://github.com/ggml-org/llama.cpp/pull/29413) ,[llama/30415](https://github.com/ggml-org/llama.cpp/pull/30415) )\n\n### Core changes\n\n- Scheduler skips uploading inputs that are not read and prefetches only inputs produced by earlier splits ([llama/31419](https://github.com/ggml-org/llama.cpp/pull/31419) ,[llama/32100](https://github.com/ggml-org/llama.cpp/pull/32100) )\n- MoE cache can compute a share of the cache misses on the CPU and copy the results back asynchronously ([llama/30966](https://github.com/ggml-org/llama.cpp/pull/30966) )\n- Meta backend raises the compute view limit for buffers with few tensors ([llama/31447](https://github.com/ggml-org/llama.cpp/pull/31447) )\n\n### Backend changes\n\n#### CUDA\n\n- Added few-row MMQ for batch sizes 2-24 and MMVF for BF16 few-row matmuls ([llama/31533](https://github.com/ggml-org/llama.cpp/pull/31533) ,[llama/31959](https://github.com/ggml-org/llama.cpp/pull/31959) )\n- Added OCP FP8 support and fused NVFP4 gate/up matmuls with GLU in MMQ ([llama/28413](https://github.com/ggml-org/llama.cpp/pull/28413) ,[llama/31296](https://github.com/ggml-org/llama.cpp/pull/31296) )\n- Extended FlashAttention with an sm70 head-size-256 config and MMA head sizes 40/72 ([llama/27997](https://github.com/ggml-org/llama.cpp/pull/27997) ,[llama/30285](https://github.com/ggml-org/llama.cpp/pull/30285) )\n- Improved graph handling: skip compat checks on reuse, re-instantiate on cluster-dim changes, move graph state ([llama/32004](https://github.com/ggml-org/llama.cpp/pull/32004) ,[llama/31284](https://github.com/ggml-org/llama.cpp/pull/31284) ,[llama/32001](https://github.com/ggml-org/llama.cpp/pull/32001) )\n- MoE: skip empty MMQ stream-k tiles, linearize the MoE layout, and sanitize post-bias NaNs ([llama/32067](https://github.com/ggml-org/llama.cpp/pull/32067) ,[llama/31047](https://github.com/ggml-org/llama.cpp/pull/31047) ,[llama/31005](https://github.com/ggml-org/llama.cpp/pull/31005) )\n- Added a debug buffer pool and halved the VMM pool reservation with reserve retries ([llama/31919](https://github.com/ggml-org/llama.cpp/pull/31919) ,[llama/30542](https://github.com/ggml-org/llama.cpp/pull/30542) )\n- HIP: use a fixed BLAS workspace and add an MFMA lightning indexer for CDNA2 ([llama/31838](https://github.com/ggml-org/llama.cpp/pull/31838) ,[llama/29050](https://github.com/ggml-org/llama.cpp/pull/29050) )\n- Added a d_state=64 SSM_SCAN fast path and made radix Top-K deterministic for ties ([llama/31818](https://github.com/ggml-org/llama.cpp/pull/31818) ,[llama/31084](https://github.com/ggml-org/llama.cpp/pull/31084) )\n\n#### Metal\n\n- Fused MoE routing and kept fusable node groups inside a single command buffer ([llama/31615](https://github.com/ggml-org/llama.cpp/pull/31615) ,[llama/31688](https://github.com/ggml-org/llama.cpp/pull/31688) )\n- Made radix Top-K deterministic for ties, added mul_mm for 32<=K<64, and switched TRI to select ([llama/31084](https://github.com/ggml-org/llama.cpp/pull/31084) ,[llama/30982](https://github.com/ggml-org/llama.cpp/pull/30982) ,[llama/30711](https://github.com/ggml-org/llama.cpp/pull/30711) )\n- Fixed GROUP_NORM for ne03>1 and out-of-bounds accesses in the FA output and SOLVE_TRI kernels ([llama/31852](https://github.com/ggml-org/llama.cpp/pull/31852) ,[llama/31662](https://github.com/ggml-org/llama.cpp/pull/31662) ,[llama/32103](https://github.com/ggml-org/llama.cpp/pull/32103) )\n\n#### Vulkan\n\n- Added an Intel FlashAttention prefill kernel ([llama/29357](https://github.com/ggml-org/llama.cpp/pull/29357) )\n- Added batched tensor copies, a test-fusion interface, and ReBAR detection ([llama/31418](https://github.com/ggml-org/llama.cpp/pull/31418) ,[llama/30769](https://github.com/ggml-org/llama.cpp/pull/30769) ,[llama/31658](https://github.com/ggml-org/llama.cpp/pull/31658) )\n- Enabled dequantized KV with CM2, YaRN truncation, RDNA3/4 large-tile split-K, and large coopmat matmul on newer AMD drivers ([llama/31526](https://github.com/ggml-org/llama.cpp/pull/31526) ,[llama/30802](https://github.com/ggml-org/llama.cpp/pull/30802) ,[llama/30280](https://github.com/ggml-org/llama.cpp/pull/30280) ,[llama/31587](https://github.com/ggml-org/llama.cpp/pull/31587) )\n- Added a tiled-transpose concat shader and FWHT kernels for block widths above 512 ([llama/30591](https://github.com/ggml-org/llama.cpp/pull/30591) ,[llama/29772](https://github.com/ggml-org/llama.cpp/pull/29772) )\n- Fixed MoltenVK out-of-bounds accesses, GROUP_NORM workgroup limits, and FA scratch sizing ([llama/31890](https://github.com/ggml-org/llama.cpp/pull/31890) ,[llama/31930](https://github.com/ggml-org/llama.cpp/pull/31930) ,[llama/30487](https://github.com/ggml-org/llama.cpp/pull/30487) )\n- Capped scalar FlashAttention at 8 rows for large heads on Qualcomm ([llama/30829](https://github.com/ggml-org/llama.cpp/pull/30829) )\n\n#### SYCL\n\n- Added a device-side MoE scheduler ([llama/30156](https://github.com/ggml-org/llama.cpp/pull/30156) )\n- Made the oneDNN FA cache thread-safe and un-gated fused SDPA for Alchemist at head_dim=64 ([llama/31138](https://github.com/ggml-org/llama.cpp/pull/31138) ,[llama/31574](https://github.com/ggml-org/llama.cpp/pull/31574) )\n- Cached the device id and reject buffers that would exceed VRAM ([llama/31126](https://github.com/ggml-org/llama.cpp/pull/31126) ,[llama/32013](https://github.com/ggml-org/llama.cpp/pull/32013) ,[llama/31285](https://github.com/ggml-org/llama.cpp/pull/31285) )\n- Added exact rounding for CPY to Q4_1/Q5_1/Q8_0, strided CLAMP, and f16 SWIGLU_OAI ([llama/31465](https://github.com/ggml-org/llama.cpp/pull/31465) ,[llama/31784](https://github.com/ggml-org/llama.cpp/pull/31784) ,[llama/30857](https://github.com/ggml-org/llama.cpp/pull/30857) )\n- Fixed AOT for allocations above 4GB ([llama/31873](https://github.com/ggml-org/llama.cpp/pull/31873) )\n\n#### OpenCL\n\n- Added decomposed Adreno FlashAttention and improved decode performance ([llama/32046](https://github.com/ggml-org/llama.cpp/pull/32046) ,[llama/31633](https://github.com/ggml-org/llama.cpp/pull/31633) )\n- Added q6_k tiled, q8_0, and f32/q5_k multi-column GEMV kernels and f32 MUL_MAT_ID ([llama/31758](https://github.com/ggml-org/llama.cpp/pull/31758) ,[llama/30947](https://github.com/ggml-org/llama.cpp/pull/30947) ,[llama/31783](https://github.com/ggml-org/llama.cpp/pull/31783) )\n- Added arange, non-contiguous sigmoid, repeat for f16/i32/i16/bf16, and DSV4 HC pre/post kernels ([llama/31829](https://github.com/ggml-org/llama.cpp/pull/31829) ,[llama/31687](https://github.com/ggml-org/llama.cpp/pull/31687) ,[llama/31782](https://github.com/ggml-org/llama.cpp/pull/31782) ,[llama/31623](https://github.com/ggml-org/llama.cpp/pull/31623) )\n- Enabled multi-column GEMV by default for Adreno X2 ([llama/31694](https://github.com/ggml-org/llama.cpp/pull/31694) )\n\n#### WebGPU\n\n- Added batched tensor API support and returned maxBufferSize from get_max_size ([llama/31473](https://github.com/ggml-org/llama.cpp/pull/31473) ,[llama/31348](https://github.com/ggml-org/llama.cpp/pull/31348) )\n- Added GROUP_NORM, MEAN, COUNT_EQUAL, and PAD_REFLECT_1D kernels ([llama/31490](https://github.com/ggml-org/llama.cpp/pull/31490) ,[llama/31591](https://github.com/ggml-org/llama.cpp/pull/31591) ,[llama/31578](https://github.com/ggml-org/llama.cpp/pull/31578) ,[llama/31877](https://github.com/ggml-org/llama.cpp/pull/31877) )\n- Supported the YaRN truncation config ([llama/30802](https://github.com/ggml-org/llama.cpp/pull/30802) )\n\n#### Hexagon\n\n- Added Q5_0/Q5_1 support and optimized conv_2d while adding conv_3d ([llama/32094](https://github.com/ggml-org/llama.cpp/pull/32094) ,[llama/31814](https://github.com/ggml-org/llama.cpp/pull/31814) )\n- Fused post-norm residual add into RMS_NORM_MUL and added set_tensor_n ([llama/31822](https://github.com/ggml-org/llama.cpp/pull/31822) ,[llama/31744](https://github.com/ggml-org/llama.cpp/pull/31744) )\n- Added automatic libhtp loading and fixed 64-bit FastRPC handle truncation ([llama/31781](https://github.com/ggml-org/llama.cpp/pull/31781) ,[llama/30952](https://github.com/ggml-org/llama.cpp/pull/30952) )\n- Fixed the host build with clang-cl on Windows ARM64 ([llama/32011](https://github.com/ggml-org/llama.cpp/pull/32011) )\n\n#### CPU\n\n- Switched MUL_MAT to F32 src1 and accumulate FlashAttention V in F32 ([llama/31854](https://github.com/ggml-org/llama.cpp/pull/31854) ,[llama/29810](https://github.com/ggml-org/llama.cpp/pull/29810) )\n- Added SpacemiT GATED_DELTA_NET RVV and Q4_1 32x256 HP kernels and enabled IME2 MXFP4 repack ([llama/31897](https://github.com/ggml-org/llama.cpp/pull/31897) ,[llama/31929](https://github.com/ggml-org/llama.cpp/pull/31929) ,[llama/31776](https://github.com/ggml-org/llama.cpp/pull/31776) )\n- Enabled the 4x4 simd_gemm tile on ARM NEON and added bf16/q8_0 VXE to llamafile ([llama/32128](https://github.com/ggml-org/llama.cpp/pull/32128) ,[llama/31866](https://github.com/ggml-org/llama.cpp/pull/31866) )\n\n#### CANN\n\n- Fail early when a buffer type is unsupported ([llama/31270](https://github.com/ggml-org/llama.cpp/pull/31270) )\n\n#### ZDNN\n\n- Accept non-zdnn tensors, invalidate compute tensors after each op, and fix release backend lib detection ([llama/31824](https://github.com/ggml-org/llama.cpp/pull/31824) ,[llama/31905](https://github.com/ggml-org/llama.cpp/pull/31905) )\n\n#### OpenVINO\n\n- Supported the YaRN truncation config ([llama/30802](https://github.com/ggml-org/llama.cpp/pull/30802) )\n\n## More info\n\n## Changelog since [v0.29.0](https://github.com/ggml-org/ggml/releases/tag/v0.29.0)\n\n[`417a024`](https://github.com/ggml-org/ggml/commit/417a024b4fb6bc3116d41af7c067166a039bdf12) ggml : bump version to 1.0.0 ([#1690](https://github.com/ggml-org/ggml/pull/1690))\n\n[`771b3d9`](https://github.com/ggml-org/ggml/commit/771b3d9c45f26d046f1149a37ad01524341857e2) requirements : fix numpy for python 3.14 ([#1691](https://github.com/ggml-org/ggml/pull/1691))\n\n[`f154959`](https://github.com/ggml-org/ggml/commit/f154959e7f1c33a4237c67783fdd360b646eeb89) sync : llama.cpp\n\n[`ec04faf`](https://github.com/ggml-org/ggml/commit/ec04faf176635c4edd0d56a7f534e6d7a94f3a22) fix(hexagon): make host build work with clang-cl on Windows ARM64 (llama/32011)\n\n[`b45738e`](https://github.com/ggml-org/ggml/commit/b45738e946d6b3eb379d2505afc2b286357591dd) examples : adapt to removal of ggml_diag_mask_inf\n\n[`1514439`](https://github.com/ggml-org/ggml/commit/1514439034c6cf8cf5d5f98a82a6d156f3786443) sync : llama.cpp\n\n[`5f29555`](https://github.com/ggml-org/ggml/commit/5f2955545ae1f454c671834d3a07b1457fe2b65f) ggml : prune (llama/29801)\n\n[`076861c`](https://github.com/ggml-org/ggml/commit/076861cdfcc5b37ffbbcaa392513786bce9d5b70) hexagon: add Q5_0 and Q5_1 support (llama/32094)\n\n[`63ec52d`](https://github.com/ggml-org/ggml/commit/63ec52d4f157f41d93aeb6ff792696f11827b187) Title: CUDA: few-row MMQ for BS 2-24 (llama/31533)\n\n[`c6fe796`](https://github.com/ggml-org/ggml/commit/c6fe79689e0c7682e182b87c1a0c3d1de55c8828) ggml : route GATED_DELTA_NET to the SpacemiT RVV kernel (llama/31897)\n\n[`4ae6e72`](https://github.com/ggml-org/ggml/commit/4ae6e7214d33a683056bac70668bb07d977fbace) vulkan : Intel FA kernel for prefill. (llama/29357)\n\n[`b22071c`](https://github.com/ggml-org/ggml/commit/b22071c095ac15a20b58e696e7a1a15b63882935) ggml-cpu: use the 4x4 simd_gemm tile on ARM NEON (llama/32128)\n\n[`ba8b013`](https://github.com/ggml-org/ggml/commit/ba8b0130435ca0c327acefffc0427b2d4aa9df6a) CUDA: Optimize prefil via fuse of w_s scale in epilogue MMQ for nvfp4 checkpoints (llama/26048)\n\n[`05f605a`](https://github.com/ggml-org/ggml/commit/05f605a25e91c30c5c85621d55f2cfb661ab7eec) ggml-backend : prefetch only inputs computed by earlier splits (llama/32100)\n\n[`b8a5b87`](https://github.com/ggml-org/ggml/commit/b8a5b871f9445d6e0ad76d18ee592b5608d1ba74) ggml : dispatch SpacemiT Q4_1 32x256 through the HP kernel (llama/31929)\n\n[`7a8cef5`](https://github.com/ggml-org/ggml/commit/7a8cef580b1078e45df3864a88cb727a26b4d0c1) sycl: make oneDNN FA cache thread-safe and memoize runtime failures (llama/31138)\n\n[`6dfea1a`](https://github.com/ggml-org/ggml/commit/6dfea1a1c5a30c3effc70bafb8692fac4f9f193d) sycl : fix AOT for more than 4GB (llama/31873)\n\n[`012ff44`](https://github.com/ggml-org/ggml/commit/012ff44a3c532e6dc61a61be6e111df5a1ecd19e) sycl : use cached device-id in set_main_device (llama/32013)\n\n[`2f9d47b`](https://github.com/ggml-org/ggml/commit/2f9d47bb172e8dddb6a5010cf45579b71e608895) CUDA: add cuda debug buffer pool (llama/31919)\n\n[`522d257`](https://github.com/ggml-org/ggml/commit/522d2575e135aa0a39a887fdceebc9573dccec17) opencl: add bin kernel `kernel_gemm_noshuffle_q4_0_f32_32b_trans_ila_a7_bin` (llama/30947)\n\n[`0f9dcb7`](https://github.com/ggml-org/ggml/commit/0f9dcb72e3b1fc31f307885cd44a586a76c5cbb1) CUDA: skip empty MoE tiles in MMQ stream-k fixup (llama/32067)\n\n[`6bed9a8`](https://github.com/ggml-org/ggml/commit/6bed9a83c1cf9273d0ce4f5f1f2fbe1d323f4c28) opencl: add decomposed FA for Adreno (llama/32046)\n\n[`a357e7b`](https://github.com/ggml-org/ggml/commit/a357e7bcddb7d7a65a58c138aaa4df6fd91c580e) metal : prevent out-of-bounds reads in SOLVE_TRI kernel (llama/32103)\n\n[`c36ccd8`](https://github.com/ggml-org/ggml/commit/c36ccd88f56b15cc000e3b34012db5784442b933) vulkan: support batched tensor copy API (llama/31418)\n\n[`1bffc59`](https://github.com/ggml-org/ggml/commit/1bffc59d478c8d0908d9e6e0d1a5887034a5e1fa) backend : re-instantiate CUDA graphs when the cluster dims of a kernel change (llama/31284)\n\n[`8153155`](https://github.com/ggml-org/ggml/commit/8153155693491f4e17c825e3dec2ef04345e52e6) ROCm/HIP: fixed BLAS workspace instead of rocBLAS allocating one per call (llama/31838)\n\n[`ad7d200`](https://github.com/ggml-org/ggml/commit/ad7d200d601b25ceb6a003c7b80d6370a01d4cd2) cpu: accumulate flash attention V in F32 (llama/29810)\n\n[`7f4a2db`](https://github.com/ggml-org/ggml/commit/7f4a2db327ccb3f517ac030a53106b3bcdd01eba) webgpu: add PAD_REFLECT_1D support (llama/31877)\n\n[`0f51454`](https://github.com/ggml-org/ggml/commit/0f514548be4eb0d0ef99a3f7ee9d9fcc992bb8a1) vulkan: allow dequantized KV optimization with CM2 (llama/31526)\n\n[`eb4de49`](https://github.com/ggml-org/ggml/commit/eb4de491b5d17b161e25fada5853770aba19d406) vulkan: allocate the device fault vendor binary buffer (llama/32008)\n\n[`6b7f47a`](https://github.com/ggml-org/ggml/commit/6b7f47aae3964d006e334c44f317a7757681edb7) cuda : use MMVF for BF16 matrices of few rows at small batch sizes (llama/31959)\n\n[`77d01f1`](https://github.com/ggml-org/ggml/commit/77d01f1ba9df7ec52a672010a4361807c0ad7eb1) cuda : add sm70 FlashAttention config case for DKQ=256, DV=256, ncols=64 (llama/27997)\n\n[`bd37ba0`](https://github.com/ggml-org/ggml/commit/bd37ba0dfd4bbedc63d2178f844e9488a52d5b04) cuda : fattn mma head sizes 40 72 (llama/30285)\n\n[`161ca15`](https://github.com/ggml-org/ggml/commit/161ca156a3846b5d176289c5196554b84baafc94) CUDA: Add OCP FP8 support (llama/28413)\n\n[`06faf80`](https://github.com/ggml-org/ggml/commit/06faf806f1b4746b01e6678f39172797a6e4d8bc) sycl : fixed sycl CLAMP to actually support strided view (llama/31784)\n\n[`a986181`](https://github.com/ggml-org/ggml/commit/a986181fe35e83cdfd7b2e8e7fa79a42cfe48996) cuda : remove unused ids and type_src0 parameters (llama/32018)\n\n[`55104b2`](https://github.com/ggml-org/ggml/commit/55104b293feb7f1cc2091cc9aa119df06ce38573) llama : Add FP8 KV-cache support (llama/28392)\n\n[`0753641`](https://github.com/ggml-org/ggml/commit/0753641f42d02d3191ff1554bcdfb5b0cf89e521) ggml : add MUL_MAT src1 precision tests and gating (llama/31896)\n\n[`1cd16bd`](https://github.com/ggml-org/ggml/commit/1cd16bd4aabb5384f48d269cec751094266c3269) cuda : remove unused quantize_cuda_t typedef (llama/31884)\n\n[`4a18cdd`](https://github.com/ggml-org/ggml/commit/4a18cdd8c807930c5d59aa3a079c034b845ebd1c) cuda : halve VMM pool reservation size and retry on cuMemAddressReserve failure (llama/30542)\n\n[`1c9ac9d`](https://github.com/ggml-org/ggml/commit/1c9ac9d88709fbc5287b09ebd582cf56ef6be50a) CUDA: skip graph compat check when graph is being reused (llama/32004)\n\n[`999c725`](https://github.com/ggml-org/ggml/commit/999c7250ec311ab031e96e1cae85876aa064a0d6) ggml : fix FreeBSD Vulkan build by setting _XOPEN_SOURCE=700 (llama/31701)\n\n[`47bc1d8`](https://github.com/ggml-org/ggml/commit/47bc1d845c141a6fe63244d01140c7248424d126) CUDA: move graph and concurrent stream state out of common.cuh (llama/32001)\n\n[`df70e12`](https://github.com/ggml-org/ggml/commit/df70e121dfa94910f616519766d40c02fd9f5f06) cann: fail early when checking if buffer type is supported (llama/31270)\n\n[`e447eb5`](https://github.com/ggml-org/ggml/commit/e447eb53592717b491d3b6f8a4b1f270af2f85f9) sycl: Add device-side MoE scheduler (llama/30156)\n\n[`9a1c582`](https://github.com/ggml-org/ggml/commit/9a1c5822a7b8cd015ef83b663cd2f91c04f50ff7) vulkan: add tiled-transpose concat shader for Qwen models (llama/30591)\n\n[`8b3c8cf`](https://github.com/ggml-org/ggml/commit/8b3c8cf97fdeb53dd151a7f4189e1937d7600b51) ggml-rpc : fail gracefully on unreachable endpoints and failed handshakes (llama/30415)\n\n[`f860f1d`](https://github.com/ggml-org/ggml/commit/f860f1ddb17a4a78235b78100cb6b7ac8e016e59) vulkan: Divide GROUP_NORM workgroup to 2D to avoid maxComputeWorkGroupCount limit (llama/31930)\n\n[`eb5571a`](https://github.com/ggml-org/ggml/commit/eb5571a3c9952efe261506f259e352ce70239f1c) vulkan: Fix out of bounds reads/writes on MoltenVK (llama/31890)\n\n[`5a9a264`](https://github.com/ggml-org/ggml/commit/5a9a2643642264c51b301dba2b916fa7e68f6520) vulkan: cap scalar flash attention at 8 rows for large heads on Qualcomm (llama/30829)\n\n[`5610f41`](https://github.com/ggml-org/ggml/commit/5610f41bb6883a57198075a250354aa8a6893339) sycl: un-gate oneDNN fused SDPA for Alchemist at head_dim=64 (llama/31574)\n\n[`487cadf`](https://github.com/ggml-org/ggml/commit/487cadf89e0eeae16926ca3e00be2ad6667f454f) hexagon: fix 64-bit FastRPC handle truncation on close (llama/30952)\n\n[`be37c9c`](https://github.com/ggml-org/ggml/commit/be37c9cf04eba02a537e313579f5870357540689) ggml-zdnn: accept non-zdnn tensors, invalidate compute tensors after every op (llama/31824)\n\n[`294d5fc`](https://github.com/ggml-org/ggml/commit/294d5fc5121ad278a4ed1e9a311f856308203e53) ggml : implement the backward pass for TRI (llama/30712)\n\n[`e18c2c6`](https://github.com/ggml-org/ggml/commit/e18c2c600a881d10549cf801c63c80a4ce98cba7) ggml-backend: don't upload inputs that are not read (llama/31419)\n\n[`e84d36b`](https://github.com/ggml-org/ggml/commit/e84d36b54b61b91663ccf64dc1e7820e5f2e5839) metal : prevent out-of-bounds writes to the Metal FA output buffer (llama/31662)\n\n[`0dd184f`](https://github.com/ggml-org/ggml/commit/0dd184f8b4e082e3c9fb2a37493aa69544dc316f) metal : make ggml_tri select instead of scaling by the comparison (llama/30711)\n\n[`b6d482c`](https://github.com/ggml-org/ggml/commit/b6d482c58b3f24982547d667f1806640c62d126b) opencl : include climits (llama/31935)\n\n[`62de780`](https://github.com/ggml-org/ggml/commit/62de7806fdcdda976bea593f8df0f84aaba54d77) RPC: Improve loading times (llama/29413)\n\n[`a7276d0`](https://github.com/ggml-org/ggml/commit/a7276d0ace8ea2b39695a50b6df4906d69647566) ggml : support YaRN truncation config on openvino, sycl, vulkan, webgpu, rpc (llama/30802)\n\n[`da89459`](https://github.com/ggml-org/ggml/commit/da894596c375d437a283f64ed2f408223335585f) sycl: cache device-id (llama/31126)\n\n[`fb57085`](https://github.com/ggml-org/ggml/commit/fb570857a9be9613870878f155877aa7a1b7b3e4) tests: bound the test_rope tolerance by the f32 angle resolution (llama/31874)\n\n[`e43d847`](https://github.com/ggml-org/ggml/commit/e43d8477bf7ef3dc9bddf98ed799b8b3628c841f) opencl: add f32 MUL_MAT_ID (llama/31783)\n\n[`d1c1e4b`](https://github.com/ggml-org/ggml/commit/d1c1e4b2c5d8f305f7d2e38bb5767391cf0cc902) ggml-zdnn: fix release binary not detecting backend lib (llama/31905)\n\n[`7e7b6e9`](https://github.com/ggml-org/ggml/commit/7e7b6e91954f1a574a1b78ec6302539e56d5f313) mtmd: refactoring: remove clip.h, consolidate code into mtmd (llama/31865)\n\n[`5a0e536`](https://github.com/ggml-org/ggml/commit/5a0e5368441ce74a30837831386e5bbafad9b596) cpu: enable SpacemiT IME2 MXFP4 dense repack (llama/31776)\n\n[`7f4b25f`](https://github.com/ggml-org/ggml/commit/7f4b25f743ec2b069b3ffd2d3176982a0bf20504) llamafile: impl bf16 and q8_0 vxe (llama/31866)\n\n[`f22fc6a`](https://github.com/ggml-org/ggml/commit/f22fc6a2c4bc87f10ae713e91dd9258701048b9d) ggml : update CUDA/Metal radix Top-K to make tied selections deterministic (llama/31084)\n\n[`47b8b4f`](https://github.com/ggml-org/ggml/commit/47b8b4fc33912bc26fcc6a8847e06b21d35487df) ggml-cuda : add d_state=64 fast path to SSM_SCAN kernel (llama/31818)\n\n[`b524960`](https://github.com/ggml-org/ggml/commit/b524960690cab0cd7e3d57ac0946ed8519e4abe7) webgpu : add COUNT_EQUAL support (llama/31578)\n\n[`75a4f5a`](https://github.com/ggml-org/ggml/commit/75a4f5abaa727eb14409f381f72b317f8aeff537) ggml : switch to F32 src1 in the CPU backend (llama/31854)\n\n[`6cddab2`](https://github.com/ggml-org/ggml/commit/6cddab2b9c0a96ec0e97f710579fefdba9c5b234) llama, mtmd: follow the reference precision of ggml_prec_set_acc calls (llama/31851)\n\n[`7353275`](https://github.com/ggml-org/ggml/commit/7353275dff29815336ddb91c7e050e7b78f43342) opencl: improve q8_0 and MoE small-n verification for spec (llama/31831)\n\n[`8f1404e`](https://github.com/ggml-org/ggml/commit/8f1404ef548189ca05d43dc55e46055104eeabd3) hexagon: support for automatic loading of libhtp without legacy env vars (llama/31781)\n\n[`91c102a`](https://github.com/ggml-org/ggml/commit/91c102a6874b8053ca914d306cee6064fb231186) sycl: exact rounding in CPY to Q4_1, Q5_1 and Q8_0 (llama/31465)\n\n[`8cf32bc`](https://github.com/ggml-org/ggml/commit/8cf32bc64abfd1beb91c78283f00d6d534a4d919) sycl: refuse device buffers that would exceed VRAM (llama/31285)\n\n[`d969b07`](https://github.com/ggml-org/ggml/commit/d969b07e20e976d2b9e9a79a65d4c0a6812904fa) hexagon: n_hvx and n_threads cleanup (llama/31857)\n\n[`5746ebd`](https://github.com/ggml-org/ggml/commit/5746ebd6dd1324269afba5afaa3986147c729e5f) llama_moe_cache: run missed experts on CPU, add tuning script (llama/30966)\n\n[`a49f174`](https://github.com/ggml-org/ggml/commit/a49f174db8e26c97f80faa818d91b47850b9c3bd) sycl: add f16 support for SWIGLU_OAI (llama/30857)\n\n[`c6a0780`](https://github.com/ggml-org/ggml/commit/c6a0780990ee695e12c1f64d7784b1fc76c30e0c) metal : fix GROUP_NORM for ne03 > 1 and non-contiguous inputs (llama/31852)\n\n[`1e5c3e0`](https://github.com/ggml-org/ggml/commit/1e5c3e03314ca8ed365053c36bd18a999f7e7207) webgpu : Implement group norm kernel (llama/31490)\n\n[`37ecdca`](https://github.com/ggml-org/ggml/commit/37ecdca3c55e11367f61ac9265099e7d65b75451) vulkan: Add 'readonly' to decodeBuf declarations. (llama/31833)\n\n[`c08538b`](https://github.com/ggml-org/ggml/commit/c08538b3a454b4c857084c6b75de30208eee8adf) CUDA: fix shared memory bank conflicts in the lightning indexer (llama/31803)\n\n[`07b8362`](https://github.com/ggml-org/ggml/commit/07b8362f961c65b5c8e719c9622d12d318994e66) opencl: add arange (llama/31829)\n\n[`f55a504`](https://github.com/ggml-org/ggml/commit/f55a5045a70e11bd57ea80c0ee6d0d92d5537f90) meta : raise the compute view limit for buffers with few tensors (llama/31447)\n\n[`2870133`](https://github.com/ggml-org/ggml/commit/2870133190dbd494804455a5cf7a0d3ebd9efdaf) hexagon: fuse post-norm residual add into RMS_NORM_MUL (llama/31822)\n\n[`a135ec6`](https://github.com/ggml-org/ggml/commit/a135ec677f7a3af22243096837eab82fb5e4b154) hexagon: conv_2d optimizations and support for conv_3d (llama/31814)\n\n[`e3d3633`](https://github.com/ggml-org/ggml/commit/e3d36332b33a302d679daa9d5da36f8e83b1ea65) tests : qualify isnan and signbit with std:: (llama/31791)\n\n[`a7d3330`](https://github.com/ggml-org/ggml/commit/a7d3330a46a9bba8c99fa6781c0e513355d19f01) tests : override hardware_concurrency in CI (llama/31797)\n\n[`ab7ca9c`](https://github.com/ggml-org/ggml/commit/ab7ca9c62d919a2787fa127598efda7001cd8f4f) opencl: support repeat for f16, i32, i16, bf16 (llama/31782)\n\n[`9290392`](https://github.com/ggml-org/ggml/commit/9290392e451010eed8c6efc39172bcdf793d306f) webgpu: add batched tensor API (`get_tensor_n` and `set_tensor_n`) (llama/31473)\n\n[`f594fed`](https://github.com/ggml-org/ggml/commit/f594fedf92ca0b49240be326aed6308d920cbe18) vulkan: detect ReBAR support, avoid BAR allocations if unavailable (llama/31658)\n\n[`38e4be2`](https://github.com/ggml-org/ggml/commit/38e4be2bf02d8949101c299a38dc141de0e980c7) CUDA: fix Maxwell build (llama/31787)\n\n[`8bd6b61`](https://github.com/ggml-org/ggml/commit/8bd6b61b7a91b3f19eca5916e3e91baf38d6913e) opencl: add q6_k multi column tiled GEMV for speculative verification and refactoring (llama/31758)\n\n[`d3ce63d`](https://github.com/ggml-org/ggml/commit/d3ce63de46431e45d1d6085802c8294b067747c2) hexagon: Implement set_tensor_n and improve repacking/tiling robustness (llama/31744)\n\n[`9b1880f`](https://github.com/ggml-org/ggml/commit/9b1880f93a7aaa5301945b80f7923f5674a5990a) ggml-cuda: sanitize post-bias NaNs in MoE selection (llama/31005)\n\n[`7e607b8`](https://github.com/ggml-org/ggml/commit/7e607b8fee548b3f68ef4ba4af4eb588c412f570) vulkan: Implement test-fusion interface (llama/30769)\n\n[`2188d13`](https://github.com/ggml-org/ggml/commit/2188d132ce259b4ced3057639c98473903280ec2) CUDA: use highest compiled arch in get_mmvq_mmid_max_batch (llama/31679)\n\n[`114ce5e`](https://github.com/ggml-org/ggml/commit/114ce5ed7e78d693403ae4e1b70f58e592ac5943) vulkan: RDNA3/4 Large-Tile Split-K Optimization (llama/30280)\n\n[`e074347`](https://github.com/ggml-org/ggml/commit/e074347a0c89f9eca517ff9aa47ad195243cc16e) metal : fuse DeepSeek-V4/V4.1 and GLM MoE routing (llama/31615)\n\n[`f0f5b42`](https://github.com/ggml-org/ggml/commit/f0f5b42042d9ddaf0bda406441cb704e9807366b) CUDA/HIP: matrix-core (MFMA) lightning indexer for CDNA2 (gfx90a) (llama/29050)\n\n[`fa8c617`](https://github.com/ggml-org/ggml/commit/fa8c6179b3663e16bcefc475e909bda73f901014) CUDA: linearize MoE data layout for MMQ/MMF (llama/31047)\n\n[`1690d2e`](https://github.com/ggml-org/ggml/commit/1690d2e166a69438d26a5fb646d620f039396437) vulkan: FWHT kernels for block widths above 512 (llama/29772)\n\n[`40278c4`](https://github.com/ggml-org/ggml/commit/40278c41a43a1162a2c348a1b57ec0b970e80413) vulkan : check combined K+V f16 scratch size in FA dequant path (llama/30487)\n\n[`2dccfdb`](https://github.com/ggml-org/ggml/commit/2dccfdb222d1ac791cc9f3461a078ce278019f1d) sync : llama.cpp\n\n[`25b845e`](https://github.com/ggml-org/ggml/commit/25b845e8d88870e85ba2176161f9da3d41f90771) ggml : support `truncate=false` for YaRN (llama/30206)\n\n[`accf2a1`](https://github.com/ggml-org/ggml/commit/accf2a1fbc78993310a61a1cd3829b17c66f5498) sync : llama.cpp\n\n[`b2ce926`](https://github.com/ggml-org/ggml/commit/b2ce926cd4b46a23fb08d384037a9c9c11844984) metal : use mul_mm for 32 <= K < 64 (llama/30982)\n\n[`1a5f477`](https://github.com/ggml-org/ggml/commit/1a5f4771609c9b6f7308a293611168085a06d726) webgpu : add MEAN support (llama/31591)\n\n[`2ab6d6c`](https://github.com/ggml-org/ggml/commit/2ab6d6c44e5050ad29f227b8c60ed448f5391d02) vulkan: Re-enable large coopmat matmul configuration on AMD proprietary driver 26.10.1+ (llama/31587)\n\n[`19df6cf`](https://github.com/ggml-org/ggml/commit/19df6cfea5755a9e3dce2923b832edeab9d56e4c) tests: fix CI flakes of TOPK_MOE caused by near ties (llama/31426)\n\n[`a0df99d`](https://github.com/ggml-org/ggml/commit/a0df99d731a720caf097fc93765b097d29c34014) metal: keep fusable node groups inside one command buffer (llama/31688)\n\n[`3a996db`](https://github.com/ggml-org/ggml/commit/3a996dba9b1a025b75cffb3c7006ea3fb193ffd4) opencl: enable f32 and q5_k multi column GEMV by default for Adreno X2 (llama/31694)\n\n[`d75184e`](https://github.com/ggml-org/ggml/commit/d75184ebf244d53f9074cd4f5e7320239ce0e466) opencl: support non-contig sigmoid (llama/31687)\n\n[`c634501`](https://github.com/ggml-org/ggml/commit/c6345010f9010fa01d790507abfd8f7a8fbe6b18) opencl: add DSV4_HC_PRE and DSV4_HC_POST (llama/31623)\n\n[`0816137`](https://github.com/ggml-org/ggml/commit/08161372fcfa4aa545a0f346d7d15af00f433f30) Title: CUDA: fuse NVFP4 gate/up matmuls and GLU in MMQ (llama/31296)\n\n[`4ac0dae`](https://github.com/ggml-org/ggml/commit/4ac0dae8acb8c8a66f10051394af051d48db939f) opencl: improve decode perf with FA (llama/31633)\n\n[`4f681f2`](https://github.com/ggml-org/ggml/commit/4f681f28cbafc27f7a1e916d0f50092963de1437) webgpu: return maxBufferSize from get_max_size and avoid whole-buffer bindings in memset/clear (llama/31348)\n\n[`cd6d2b7`](https://github.com/ggml-org/ggml/commit/cd6d2b75f5d3e4b2f3fe8e8fbc6c8b84ac80e74a) docs : sync ggml_type enum in gguf.md ([#1685](https://github.com/ggml-org/ggml/pull/1685))", "url": "https://wpnews.pro/news/ggml-v1-0-0", "canonical_source": "https://github.com/ggml-org/ggml/releases/tag/v1.0.0", "published_at": "2026-11-14 02:28:29+00:00", "updated_at": "2026-11-14 02:50:31.151290+00:00", "lang": "en", "topics": ["machine-learning", "ai-infrastructure", "large-language-models", "ai-tools"], "entities": ["ggml", "llama.cpp", "CUDA", "Vulkan", "SYCL", "OpenCL", "WebGPU", "Hexagon"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/ggml-v1-0-0", "markdown": "https://wpnews.pro/news/ggml-v1-0-0.md", "text": "https://wpnews.pro/news/ggml-v1-0-0.txt", "jsonld": "https://wpnews.pro/news/ggml-v1-0-0.jsonld"}}