ggml-org/llama.cpp

ggml : make quantization bit-reproducible across compilers and architectures (-ffp-contract=off on ggml-quants.c) ggml

Add E8 lattice 2-bit KV cache quantization (GGML_TYPE_E8_2) documentation ggml Apple Metal CUDA

vulkan : check src0 type in GGML_OP_SET_ROWS to avoid failures due to unimplemented f16 support Vulkan ggml

server : add timings and progress to responses stream server

ggml-cpu: detect AVX-VNNI in MSVC native builds ggml

ggml : add support for CPU f16->f16 GGML_OP_SET_ROWS testing ggml

OpenCL: fix sub_group_shuffle_xor compatibility for Qualcomm Adreno GPUs ggml OpenCL

GigaChat 3.5 model testing conversion

cann: upgrade flash attention to V5 and add SWIGLU_OAI/ADD_ID ops devops ggml Ascend NPU

ui: Context usage gauge and panel server/ui

vulkan: Use native e2m1 and e4m3 conversions for mxfp4/nvfp4 Vulkan ggml

perplexity : Printing PPL when stride is used (#25335) [no release] examples

ggml : add E4M3 (fp8) CPU quantization type testing examples ggml Apple Metal conversion

fix: load qwen35 Ollama GGUF exports model

chat : allow gpt-oss non-streaming final without channel markup (#25321) testing

llama_dsv4: write only used rows in state

ggml : use kernel type for conv_1d im2col to support f32 ggml

server: eagerly create prompts log directory at startup server

ggml: asynchronous scheduler memory copies ggml CUDA

SYCL: oneDNN SDPA Flash Attention for Quantized KV Caches documentation ggml SYCL

loader: map sparse mmap tensor ranges

json-schema-to-grammar: harden _visit_pattern against malformed regex patterns

kv-cache : fix SWA state save/load round-trip past n_swa

llama : stream MoE routed experts from disk

llama-batch: enable parallel sequences for partial rollback model

common : resolve non-positive --threads to the number of math cores documentation testing server

CANN: Refactor `#ifdef` blocks to avoid unreachable code after `return` ggml Ascend NPU

ggml, server: add ggml_backend_dev_reset() for sleep mode Vulkan server ggml SYCL Apple Metal Ascend NPU OpenCL IBM zDNN Hexagon CUDA AMD ZenDNN OpenVINO WebGPU

[SYCL] support OP OPT_STEP_ADAMW, OPT_STEP_SGD documentation ggml merge ready SYCL

[SYC:] support op get_rows_back, only support fp32/fp16 documentation ggml SYCL