All entries

HIP: broaden MoE ncols_opt tile heuristic on RDNA3.5 architecture (#28935) It's found the MoE ncols_opt tile heuristic needs to be broadened to include the RDNA3.5 architecture. The code change is imp

qwen4exp: add hc ops (#28901) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47897353 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, Kl

Change max context length for auto-fitting with unified KV (#28849) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47906437 macOS/iOS: macOS Apple Silicon

rpc : invalidate cached compute graph when a referenced buffer is freed (#24292) The server caches the most recent compute graph per device so that GRAPH_RECOMPUTE can re-execute it without resending

spacemit : fix wrong transpose function for int16 data (#25161) The sizeof(int16_t) branch in permute_transpose_impl calls rvv_transposed_s32_mn_to_nm instead of rvv_transposed_s16_mn_to_nm. This is a

CUDA/HIP: improve access patterns in im2col (#28013) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47937267 macOS/iOS: macOS Apple Silicon (arm64) macOS A

model : add support for HrmTextForCausalLM (DFM Mimir 1B) (#27625) model : add support for HrmTextForCausalLM (DFM Mimir 1B) HRM-Text runs two transformer stacks (low, high) in an alternating cycle ov

hexagon: accept the zeroed rope probe in supports_op (#28995) llama probes weight placement with a rope where all params are 0, so rejecting n_dims == 0 or freq_base == 0 puts rope_freqs on the CPU. T

hexagon: Support for K-Quants Q4_K and Q6_K (#28994) implement q6k/q4k kernels Squashed from: feat: implement q6k kernel hex-q6k: improve unpack accuracy hex-q4_k: add support for Q4_K kernels Co-auth

Enable CUDA graph for MTP draft (#28549) Improve CUDA graph usage for MTP Rename field Address review feedback Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestatio

TP: fix split state and granularity for fused QKV gemma4, qwen35 (#28965) model: calculate split states for attn_qkv from n_head * n_embd_head_k required for gemma4 with --fuse-qkv, where n_embd is 53

model is one package with three jobs: the contract between the runner and the architectures, the opened checkpoint, and building nn layers from checkpoint tensors. Its files did not say which was whic

ci : fix android release (#28936) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47548995 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64

ci: Bump CUDA Windows x64 builds to 13.4.1 (#28930) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47583571 macOS/iOS: macOS Apple Silicon (arm64) macOS Ap

metal : add FA kernels for HSK=96, HSV=64 (MiniCPM3) (#28599) metal : add FA kernels for HSK=96, HSV=64 (MiniCPM3) MiniCPM3 sets attention.key_length to 96 and does not set attention.value_length, whi

opencl: add generic ssm_scan (#28881) opencl: add generic ssm_scan opencl: fix whitespace Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47601188 macOS/iOS

OpenVINO: optimize stateful decode and GPU MoE inference (#28638) exclude GPU/NPU failing POOL_2D case Fix pool case ggml-openvino: fix stateful decode for Gemma-4 per-layer-type head sizes ggml-openv

vulkan: support sparse Flash Attention (#28105) vulkan: add sparse Flash Attention support for DSV4/GLM tune implementation add tests avoid nondeterministic atomicAdd add cm2 decode vector support sim

models : move build_arch_graph() after graph() template specialization (#28934) Move build_arch_graph()'s function definitions after the graph and graph template specializations have been explicitly d

cuda: support row-contiguous SUM_ROWS (#26308) cuda: support row-contiguous SUM_ROWS organize the code and add GGML_OP_MEAN to support row-contiguous tensors using the same shared kernel, and add a te

rpc : hash-cache only weights (#28789) rpc : hash-cache only weights ggml_backend_rpc_buffer_set_tensor and ggml_backend_rpc_set_tensor_async hashed every transfer above HASH_THRESHOLD and let rpc-ser

opencl: choose the MoE expert matmul by batch size for speculative decoding/MTP (#27637) opencl: gate the prebuilt q4_0 MoE GEMM on routing count opencl: stop writing zeros into the padded MoE activat

HIP: Enable AllReduce for ROCm (#27825) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47762387 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon

hex-cpy: use dma if src and dst are contiguous (#28906) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47770889 macOS/iOS: macOS Apple Silicon (arm64) macO

hexagon: add back missing contiguous fast-path and hvx_copy_uu for each run (#28886) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47775478 macOS/iOS: mac

What's Changed app: fix ChatGPT model selector spacing mlxrunner: Evict prefix cache snapshots from the active conversation mlxrunner: check system free memory and wait for evicted runners before load

**Release Tag:** v0.34.2‑rc0 (commit `b10969`) **Key Details:** This release candidate bumps the version of *llama.cpp* and addresses a build issue where duplicate symbols were generated between `libl

ggml-cuda: fallback to F32 on device without BF16 hardware acceleration (#28846) ggml-cuda: fallback to F32 on device without BF16 hardware acceleration: (Nvidia >= AMPERE, AMD >= RDNA3 or = CDNA) app

common : move llama_n_rs_seq to before llama_decode (#28749) This commit moves the llama_n_rs_seq function call to before the llama_decode call and returns directly if the check is true, removing the

sycl : fix oneDNN scratchpad breaking the pool free order (#28704) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47287268 macOS/iOS: macOS Apple Silicon (

ggml-cpu : disable PCH and fix CACHE_LINE_SIZE ambiguity to fix heap corruption (#28882) Disable the ggml-cpu precompiled header and remove the std::hardware_destructive_interference_size branch from

sycl: rfc: Use radix select for top_k (#28670) sycl: GPU-resident TOP_K for large k, parallelised over the device The SYCL backend refused GGML_OP_TOP_K above k = 32 and let it fall back to the CPU, a

llama.cpp : bump version to 0.4.1 (#28900) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47376843 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silic

ci : add ubuntu-cuda builds to release (#28186) release : add ubuntu-cuda build job (12.8/13.3, x64+arm64) Add GCC 14 for CUDA arm64 builds in CI Eplicit bash Install git for CCCL fetch Install git be

HIP: fattn-mma: use fp32 accumulation on MFMA devices (#28576) use fp32 accumulators in fattn-mma on CDNA Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47

**Release:** `v0.34.1‑rc0` (release candidate). **Repository:** `ollama/ollama`. **Key changes:** The release bumps the MLX library version, adds support for `ModelOpt` global scales in Mixture-of-Exp

Overview llama.cpp 0.4.1 adds Maple 20B-A1B, Tencent Hy 4, and Spark2.5 support, improves JSON schema handling, chat parsing, logging, and server child-process management, and updates ggml to v0.24.0.

common : implement common_schema internal representation for JSON schemas (#28736) common : implement common_schema types common : implement a json schema optimizer common : reduce optimizations commo

common: add LOG_JSON macro to log structured data (#28586) add LOG_JSON macro fit: add demo LOG_JSON Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/4711287

chat : improve parsing of complex types in qwen3-coder (#28742) chat : improve schema support in qwen3 parser cont : clean up grammar a bit Website: https://llama.app Attestations: https://github.com/

opencl: apply the noshuffle row-alignment rule to q4_K, q5_K and q8_0, not just q6_K (#28575) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47132459 macOS

vulkan: workaround NV queuesubmit driver bug (#28830) There is a driver bug where two queues on the same VkDevice simultaneously submitting can break some internal synchronization. Until it's fixed, a

tests : reduce FA test sizes (#28842) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47152933 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (a

sycl : Fix get mem error (#28227) fix for unsupport zes API optimize the code adjust the log level rm unused head files Update docs/backend/SYCL.md Co-authored-by: Titaniumtown titaniumtown@proton.me

ggml-cpu(s390x): guard VXE-only repack helpers (#28775) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47190488 macOS/iOS: macOS Apple Silicon (arm64) macO

models : guard the expert FFN size fallback in nemotron-h against a zero divisor (#28779) The NextN/MTP tail loop derives the expert FFN size as n_ff/n_expert_used when expert_feed_forward_length give