llama.cpp Releases
684 releases of ggml-org/llama.cpp
- b10034
Fixes a bug in OpenCL MoE (Mixture of Experts) kernels for specific Adreno GPU architectures that were causing corrupted output.
Jul 15, 2026
- b10032
Adds a new CUDA implementation for the lightning indexer operation using generic vector and WMMA kernels, with architectural relaxations and refactoring.
Jul 15, 2026
- b10031
Removes a mutual-exclusion check for the `--stdin` tokenization flag to align CLI behavior with completion scripts.
Jul 15, 2026
- b10025
Relaxes tensor contiguity requirements for CUDA quantized concatenation operations, allowing for more flexible memory layouts.
Jul 15, 2026
- b10021
Optimizes DeepseekV4 graph splitting logic to reduce overhead, improving performance for inference tasks on this specific model architecture.
Jul 15, 2026
- b10020
Fixes data retrieval issues in SYCL for specific quantization types, ensuring correct tensor operations.
Jul 15, 2026
- b10019
Adds support for FP16 kernel types in SYCL for depthwise convolution operations, enhancing precision handling.
Jul 15, 2026
- b10018
Implements a new `xielu` operation for the SYCL backend, expanding the library's capability for specific computational kernels.
Jul 15, 2026
- b10017
Adjusts SYCL memory allocation thresholds to handle larger models running on devices with limited VRAM, improving stability for systems with memory overcommitment.
Jul 15, 2026
- b10016
Introduces Flash Attention support for the SYCL backend using the XMX engine and oneDNN graph API, significantly improving prefill speeds on Battlemage architecture.
Jul 15, 2026
- b10015
A minor maintenance update fixing an OpenCL compatibility issue and releasing standard binaries for all supported platforms.
Jul 15, 2026
- b10012
A maintenance release addressing a Hexagon signal enum narrowing issue and providing standard binary builds across macOS, Linux, Android, Windows, and openEuler platforms.
Jul 14, 2026
- b10011
Refactored prompt cache state ownership in the server by moving prompt state data to `server_prompt_cache` and adding handling for batched slot clearing.
Jul 14, 2026
- b10010
Added `--cors-*` options to the server to allow configuration of CORS headers, including a special 'localhost' value, with accompanying tests.
Jul 14, 2026
- b10007
Fixed a bug in the OpenCL backend where it failed to initialize on devices without the `cl_khr_integer_dot_product` extension by preventing the use of unavailable dot product kernels.
Jul 14, 2026
- b10005
Fixed sequence management issues in the DeepseekV4 implementation, specifically correcting `seq_rm` and implementing proper `seq_cp` and update context logic.
Jul 14, 2026
- b10004
Added full support for f16 as SET_ROWS source in the Vulkan and CPU backends, improving compatibility and fixing denormalized number handling on Intel GPUs.
Jul 14, 2026
- b10003
Refactored the tokenize tool to use shared argument parsing (`common_params_parse`) for consistency, exposing new model sourcing and tokenization flags.
Jul 14, 2026
- b10002
Adds a set of utility functions to check the contiguity of inner tensor dimensions and releases standard binaries for supported platforms.
Jul 14, 2026
- b10001
Fixes a critical segfault in the `test-export-graph-ops` test when called without arguments and releases standard binaries for supported platforms.
Jul 14, 2026