b11480
llama : add a GPU cache for MoE experts kept in host memory (#29887) llama : add a GPU cache for MoE experts kept in host memory Assisted-by: Claude use llama_moe_cache_ptr Website: https://llama.app
Knowledge catalogue
llama : add a GPU cache for MoE experts kept in host memory (#29887) llama : add a GPU cache for MoE experts kept in host memory Assisted-by: Claude use llama_moe_cache_ptr Website: https://llama.app
mtmd: add cohere2 vision support (#30062) cohere2 vision model address comments remove redundant mapping follow existing patterns fused linear_1 Website: https://llama.app Attestations: https://github
cuda: FWHT kernels for block widths above 512 (#29100) The CUDA FWHT covers widths 64 to 512. It runs one row per warp and keeps N/32 values per lane, so wider blocks need more registers per lane than
model : add LiquidAI/d1-3B decision model (#30110) model : add LiquidAI/d1-3b decision model mtmd : read LFM2 image resize algo from GGUF Assisted-by: Claude Opus 5.5 common : rename decision type d1
chat : name tool and argument parser rules by index (#30088) bugfix: infinite recursion caused by a tool named 'call'(#29967) chat : use index for schema and argument rules tests : remove tests tests
chat: fix jinja parser for TranslateGemma (#30096) chat: fix jinja parser for translategemma log if missing soruce_lang_code or target_lang_code Website: https://llama.app Attestations: https://github
hexagon: improved GELU accuracy (#30104) Assisted-by: OpenCode Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53797268 macOS/iOS: macOS Apple Silicon (arm6
hexagon: support tiled Q4_K and Q6_K GET_ROWS (#30115) hexagon: support tiled Q4_K GET_ROWS Assisted-by: OpenCode properly reject Q4_K views Assisted-by: OpenCode hexagon: support tiled Q6_K GET_ROWS
model : add LiquidAI/d1-omni-600M decision model (#30114) model : add LiquidAI/d1-omni-600M decision model Assisted-by: Claude Opus 5.5 mtmd : keep conformer GLU sigmoid on CUDA Assisted-by: Claude Op
hexagon: Q6_K weight dequant speedup (#30121) hexagon: Q6_K weight dequant speedup Assisted-by: OpenCode unroll by another factor of 2 Assisted-by: OpenCode Website: https://llama.app Attestations: ht
hexagon: enable alloc_buffer_n (#30126) hex-bufs: add support for alloc_buffer_n hex-bufs: add support for splitting large tensors into separate buffers hex-bufs: update GGML_HEXAGON_MBUF to accept th
sycl: remove duplicate block-size defines from op headers (#29507) All were duplicates of the values in ggml/src/ggml-sycl/presets.hpp Website: https://llama.app Attestations: https://github.com/ggml-
sycl: add grouped MoE XMX GEMM (#29245) Co-authored-by: cwriter cwriter@localhost Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53864714 macOS/iOS: macOS
sycl: fuse the delta-net alpha gate (add + unary + mul) (#29687) sycl: fuse the delta-net alpha gate (add + unary + mul) tests: cover the fused add + unary + mul chain sycl: give the fused alpha gate
CUDA: fix norm family kernels when ne[2]/ne[3] exceed grid dim limits (#28175) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53919465 macOS/iOS: macOS App
cuda : Use byte strides for roll to allow non-contiguous ROLL operations (#29547) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53926988 macOS/iOS: macOS
hex-mmadd: do not assume aligned read/write when bias-add is fused (#30133) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53932639 macOS/iOS: macOS Apple
sycl: FWHT optimizations (#29605) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53938516 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64
vendor : update cpp-httplib to 0.60.1 (#30134) Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53949333 m
vulkan : fix TOP_K for +inf/NaN inputs and k = 1 on negative values (#30107) The bucket search in topk_nary_search.comp started from the range [0, 0xFF800000), which ends just below the ordered-uint m
llama: support MoE cache over multiple GPUs (#30112) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53988921 macOS/iOS: macOS Apple Silicon (arm64) macOS A
CUDA: fix CCCL version guard breaking on major version rollover (#29453) CUDA: fix CCCL version guard breaking on major version rollover The guard compared the major and minor components independently
CUDA : looped PAD kernel for more than 65535 rows or slices (#30147) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54006924 macOS/iOS: macOS Apple Silicon
CUDA: fix MMQ out-of-bounds reads (#29953) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54029251 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silic
model : fix DFlash output head sharing (#30111) llama : fix DFlash output head sharing Assisted-by: Codex dflash : read tied output weights from GGUF metadata Assisted-by: Codex llama : share tied wor
CUDA: improve top-k algorithm selection (#28713) CUDA: radix top-k for large row counts Replaces CUB's per-row DeviceTopKKernel with a grid-over-rows radix select, gated on GGML_CUDA_TOPK_RADIX_MIN_RO
Musa FWHT fix (#30167) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54083178 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI
I spent the past year independently building Slow Vale, an LLM-driven life simulation. The Chinese server now has 800+ AI residents sharing one continuously running city. This is an engineering write-
ggml-webgpu: no dawn native features on wasi (#27069) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53445261 macOS/iOS: macOS Apple Silicon (arm64) macOS
sycl: add IQ3_S multi-column MMVQ (#29500) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53455527 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silic
vulkan: fix amd iGPU slow checkpoint read (#30049) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53465294 macOS/iOS: macOS Apple Silicon (arm64) macOS App
ggml-webgpu: fix flash_attn supports_op check for overlapping KV (#28205) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53548008 macOS/iOS: macOS Apple Si
imatrix : include clocale for std::setlocale (#30079) Co-authored-by: yarik dazzywi@github.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53551657 macO
vendor : update cpp-httplib to 0.60.0 (#30081) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53557265 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple S
musa: use the tile lightning indexer kernel (#30080) Signed-off-by: Xiaodong Ye xiaodong.ye@mthreads.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/535
vocab : add plamo fim tokens (#30090) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53567889 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (a
sampling : use greedy selection for eligible temperature-zero chains (#29797) sampling : use greedy selection for eligible temperature-zero chains Assisted-by: OpenAI Codex Apply suggestion from @gger
feat: add GLM5Next MTP, optimize (#29928) llama : add GLM5-Next NextN (MTP) graph Build the GLM5-Next multi-token-prediction head as graph_mtp: the NextN block embeds enorm(tok)+hnorm(h) through eh_pr
metal : fix MUL_MAT+ADD fusion when the residual is itself a MUL_MAT (#30100) metal : fix MUL_MAT+ADD fusion when the residual is itself a MUL_MAT ggml_metal_op_mul_mat_mma picks the residual of a fus
metal : few-row MMA mat-mul for the remaining src0 types (#30065) The generic few-row MMA kernel works for any type with a 16-weight dequantizer, so it now also takes BF16, Q1_0, Q2_0, MXFP4, Q2_K, Q3
llama: fix k-pool scatter data race on shared sequences (#29994) llama: re-pool each shared k-pool rep once With shared cells every pool is re-pooled, and since the pooled keys are always scattered, t
test-llama-archs : initialize backends before generating models (#30034) With GGML_BACKEND_DL=ON, backends must be loaded explicitly before creating models. Assisted-by: Codex Website: https://llama.a
ggml: refactor selective expert copying to user code (#29943) ggml: refactor selective expert copying to user code tests: enroll two models into selective expert copy test tests: use deepseek2 as test
llama : re-reserve the sched when the nextn extraction flags change (#30020) The speculative MTP init enables NextN extraction on the target and draft contexts after both were created and their schedu
models : consolidate nextn row cropping into shared helpers (#30017) mimo2 : always emit h_nextn the other nextn-capable models set it unconditionally Assisted-by: pi:llama.cpp/MiMo-V2.6-Flash-MOPD mo
ggml: fix CLAMP on non-contiguous views (CPU, CUDA) (#29517) ggml: fix CLAMP on non-contiguous views (CPU, CUDA) CUDA clamped ggml_nelements values flat and ignored the view strides. CPU addressed row
RPC: add -sm tensor (#26610) rpc: allow -sm tensor fix flush for apple rdma move graph_uids to rpc_dispatcher cont : fix conflict cont: stop spinning dispatcher thread remove meta backend change add T
opencl: fix OOB read in adreno xmem GEMM (#30041) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53310534 macOS/iOS: macOS Apple Silicon (arm64) macOS Appl
model : add K2 Horizon dense and MoVA support (#29535) model: K2 Horizon gguf conversion code model: loading hparams and tensors in k2-horizon.cpp model: K2 Horizon compute graph model: K2 Horizon com
vocab : implement PLaMo-3 tokenizer pre-segmentation (#30045) vocab : implement PLaMo-3 tokenizer pre-segmentation The PLaMo-3 tokenizer inserts hard boundaries before running the Unigram DP, around <
cuda : add BF16 support for XIELU (#29955) The XIELU CUDA kernel template is already generic over the element type; only the F32/F16 type assertion and the else-if dispatch were missing. Add the nv_bf
llama: support both embd + raw tokens in batch (#29622) llama: support both embd + raw tokens in batch add to test-llama-archs also check case llm_arch_supports_mixed_batch = false constant graph topo
log, server: self contained colors, split child commands from logs in router mode (#29895) log, server: make router child lines carry their own colors The logger writes the color reset after the trail
CUDA: prefer whole-tile FlashAttention scheduling for efficient two-stage kernels (#29435) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52707115 macOS/iO
CUDA: use MMVF for thin f16/bf16 mul_mat at small batch size (#29633) CUDA: use MMVF for thin f16/bf16 mul_mat at small batch size Signed-off-by: ynankani ynankani@nvidia.com adjust kernel selection l
metal : few-row MMA mat-mul (#29869) metal : few-row MMA mat-mul and batched copies for speculative decoding Speculative decoding verifies a few draft tokens per step. Without the tensor API, Metal ra
cuda: tile the lightning indexer over keys and tokens for 4 heads (#29901) cuda: tile the lightning indexer over keys and tokens for 4 heads With too few heads for a wmma tile, a block scores 64 keys
webgpu: add MMVQ support for Q1_0/Q5_0/Q5_1/Q3_K/Q5_K/Q6_K/MXFP4 (#29483) add supports for q1/q5/q3_k/q5_k/q6_k/mxfp4 of mmvq path Add K_QUANTS_HANDLING macro to q1_0 of mmvq path Website: https://lla
vulkan : Fix undeclared identifiers when -DGGML_VULKAN_RUN_TESTS=ON (#29912) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52752005 macOS/iOS: macOS Apple
ggml-cpu : add Q8_0 IME1 matrix kernel for SpacemiT X60 (#28479) ggml-cpu : add Q8_0 IME1 matrix kernel for SpacemiT X60 On the SpacemiT X60, IME matrix acceleration only covered Q4_0/Q4_1/Q4_K. Q8_0