ggml-org_llama.cpp

Author	SHA1	Message	Date
Piotr Wilkin (ilintar)	98ae0a0d36	common/parser: fix handling of tool definition with missing properties key (#21128 )	2026-03-28 20:41:32 +01:00
Aldehir Rojas	312d870a89	common : replace wrap_for_generation with a prefix convenience function and fix gpt-oss (#20912 )	2026-03-23 22:21:47 -05:00
James O'Leary	76f2dc70c3	chat : handle tool calls with no required args in TAG_WITH_TAGGED format (#20764 ) * chat : handle tool calls with no required args in TAG_WITH_TAGGED format * Update tests/test-chat.cpp [no ci] Co-authored-by: Aldehir Rojas <hello@alde.dev> --------- Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com> Co-authored-by: Aldehir Rojas <hello@alde.dev>	2026-03-19 17:53:11 +01:00
Piotr Wilkin (ilintar)	5e54d51b19	common/parser: add proper reasoning tag prefill reading (#20424 ) * Implement proper prefill extraction * Refactor cli parameters, update docs, move reasoning budget sampler part to common/reasoning-budget.cpp * Update tools/server/server-task.cpp * refactor: move grammars to variant, remove grammar_external, handle exception internally * Make code less C++y Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2026-03-19 16:58:21 +01:00
Piotr Wilkin (ilintar)	1430c35948	common/parser: gracefully handle undetected tool parser, print error message. (#20286 ) Build Actions Cache / ubuntu-24-vulkan-cache (push) Has been cancelled Details Build Actions Cache / ubuntu-24-spacemit-cache (push) Has been cancelled Details Build Actions Cache / windows-2022-rocm-cache (push) Has been cancelled Details CI / macOS-latest-cmake-arm64 (push) Has been cancelled Details CI / macOS-latest-cmake-x64 (push) Has been cancelled Details CI / macOS-latest-cmake-arm64-webgpu (push) Has been cancelled Details CI / ubuntu-cpu-cmake (arm64, ubuntu-22.04-arm) (push) Has been cancelled Details CI / ubuntu-cpu-cmake (ppc64le, ubuntu-24.04-ppc64le) (push) Has been cancelled Details CI / ubuntu-cpu-cmake (s390x, ubuntu-24.04-s390x) (push) Has been cancelled Details CI / ubuntu-cpu-cmake (x64, ubuntu-22.04) (push) Has been cancelled Details CI / ubuntu-latest-cmake-sanitizer (Debug, ADDRESS) (push) Has been cancelled Details CI / ubuntu-latest-cmake-sanitizer (Debug, THREAD) (push) Has been cancelled Details CI / ubuntu-latest-cmake-sanitizer (Debug, UNDEFINED) (push) Has been cancelled Details CI / ubuntu-latest-llguidance (push) Has been cancelled Details CI / ubuntu-latest-cmake-rpc (push) Has been cancelled Details CI / ubuntu-24-cmake-vulkan-deb (push) Has been cancelled Details CI / ubuntu-24-cmake-vulkan (push) Has been cancelled Details CI / ubuntu-24-cmake-webgpu (push) Has been cancelled Details CI / ubuntu-24-wasm-webgpu (push) Has been cancelled Details CI / ubuntu-22-cmake-hip (push) Has been cancelled Details CI / ubuntu-22-cmake-musa (push) Has been cancelled Details CI / ubuntu-22-cmake-sycl (push) Has been cancelled Details CI / ubuntu-22-cmake-sycl-fp16 (push) Has been cancelled Details CI / build-linux-cross (push) Has been cancelled Details CI / build-cmake-pkg (push) Has been cancelled Details CI / macOS-latest-cmake-ios (push) Has been cancelled Details CI / macOS-latest-cmake-tvos (push) Has been cancelled Details CI / macOS-latest-cmake-visionos (push) Has been cancelled Details CI / windows-msys2 (Release, clang-x86_64, CLANG64) (push) Has been cancelled Details CI / windows-msys2 (Release, ucrt-x86_64, UCRT64) (push) Has been cancelled Details CI / windows-latest-cmake (arm64, llvm-arm64, -G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON) (push) Has been cancelled Details CI / windows-latest-cmake (arm64, llvm-arm64-opencl-adreno, -G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" -DGGML_OPENCL=ON -DGGML_OPENCL_USE_ADRENO_KERNELS=ON) (push) Has been cancelled Details CI / windows-latest-cmake (x64, cpu-x64 (static), -G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DBUILD_SHARED_LIBS=OFF) (push) Has been cancelled Details CI / windows-latest-cmake (x64, openblas-x64, -G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_OPENMP=OFF -DGGML_BLAS=… (push) Has been cancelled Details CI / windows-latest-cmake (x64, vulkan-x64, -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_VULKAN=ON) (push) Has been cancelled Details CI / ubuntu-latest-cmake-cuda (push) Has been cancelled Details CI / windows-2022-cmake-cuda (12.4) (push) Has been cancelled Details CI / windows-latest-cmake-sycl (push) Has been cancelled Details CI / windows-latest-cmake-hip (push) Has been cancelled Details CI / ios-xcode-build (push) Has been cancelled Details CI / android-build (push) Has been cancelled Details CI / android-ndk-build (arm64-cpu, -D ANDROID_ABI=arm64-v8a -D ANDROID_PLATFORM=android-31 -D CMAKE_TOOLCHAIN_FILE=${ANDROID_NDK_ROOT}/build/cmake/android.toolchain.cmake -D GGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv8.5-a+fp16+i8mm -G Ninja -D LLAMA_OPENSSL=O… (push) Has been cancelled Details CI / android-ndk-build (arm64-snapdragon, --preset arm64-android-snapdragon-release) (push) Has been cancelled Details CI / openEuler-latest-cmake-cann (aarch64, Release, 310p, off) (push) Has been cancelled Details CI / openEuler-latest-cmake-cann (aarch64, Release, 910b, off) (push) Has been cancelled Details CI / openEuler-latest-cmake-cann (aarch64, Release, 910b, on) (push) Has been cancelled Details CI / openEuler-latest-cmake-cann (x86, Release, 310p, off) (push) Has been cancelled Details CI / openEuler-latest-cmake-cann (x86, Release, 910b, off) (push) Has been cancelled Details CI / openEuler-latest-cmake-cann (x86, Release, 910b, on) (push) Has been cancelled Details CI / ggml-ci-x64-cpu-low-perf (push) Has been cancelled Details CI / ggml-ci-arm64-cpu-low-perf (push) Has been cancelled Details CI / ggml-ci-x64-cpu-high-perf (push) Has been cancelled Details CI / ggml-ci-arm64-cpu-high-perf (push) Has been cancelled Details CI / ggml-ci-arm64-cpu-high-perf-sve (push) Has been cancelled Details CI / ggml-ci-x64-nvidia-cuda (push) Has been cancelled Details CI / ggml-ci-x64-nvidia-vulkan-cm (push) Has been cancelled Details CI / ggml-ci-x64-nvidia-vulkan-cm2 (push) Has been cancelled Details CI / ggml-ci-x64-cpu-amx (push) Has been cancelled Details CI / ggml-ci-mac-metal (push) Has been cancelled Details CI / ggml-ci-mac-webgpu (push) Has been cancelled Details CI / ggml-ci-mac-vulkan (push) Has been cancelled Details CI / ggml-ci-x64-linux-intel-vulkan (push) Has been cancelled Details CI / ggml-ci-arm64-cpu-kleidiai (push) Has been cancelled Details CI / ubuntu-cpu-cmake-riscv64-native (push) Has been cancelled Details CI / ubuntu-cmake-sanitizer-riscv64-native (Debug, ADDRESS) (push) Has been cancelled Details CI / ubuntu-cmake-sanitizer-riscv64-native (Debug, THREAD) (push) Has been cancelled Details CI / ubuntu-cmake-sanitizer-riscv64-native (Debug, UNDEFINED) (push) Has been cancelled Details CI / ubuntu-llguidance-riscv64-native (push) Has been cancelled Details CI / ubuntu-cmake-rpc-riscv64-native (push) Has been cancelled Details CI / ggml-ci-arm64-graviton4-kleidiai (push) Has been cancelled Details EditorConfig Checker / editorconfig (push) Has been cancelled Details Release / macOS-arm64 (push) Has been cancelled Details Release / macOS-x64 (push) Has been cancelled Details Release / ubuntu-22-cpu (s390x, ubuntu-24.04-s390x) (push) Has been cancelled Details Release / ubuntu-22-cpu (x64, ubuntu-22.04) (push) Has been cancelled Details Release / ubuntu-22-vulkan (push) Has been cancelled Details Release / windows-cpu (arm64) (push) Has been cancelled Details Release / windows-cpu (x64) (push) Has been cancelled Details Release / windows (arm64, opencl-adreno, -G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" -DGGML_OPENCL=ON -DGGML_OPENCL_USE_ADRENO_KERNELS=ON, ggml-opencl) (push) Has been cancelled Details Release / windows (x64, vulkan, -DGGML_VULKAN=ON, ggml-vulkan) (push) Has been cancelled Details Release / windows-cuda (12.4) (push) Has been cancelled Details Release / windows-cuda (13.1) (push) Has been cancelled Details Release / windows-sycl (push) Has been cancelled Details Release / ubuntu-22-rocm (7.2, x64, gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101;gfx1151;gfx1150;gfx1200;gfx1201) (push) Has been cancelled Details Release / windows-hip (gfx1150;gfx1151;gfx1200;gfx1201;gfx1100;gfx1101;gfx1102;gfx1030;gfx1031;gfx1032, radeon) (push) Has been cancelled Details Release / ios-xcode-build (push) Has been cancelled Details Release / openEuler-cann (aarch64, Release, 310p, off) (push) Has been cancelled Details Release / openEuler-cann (aarch64, Release, 910b, on) (push) Has been cancelled Details Release / openEuler-cann (x86, Release, 310p, off) (push) Has been cancelled Details Release / openEuler-cann (x86, Release, 910b, on) (push) Has been cancelled Details Server-Metal / server-metal (GPUx2, backend-sampling) (push) Has been cancelled Details Server-Metal / server-metal (GPUx2) (push) Has been cancelled Details Server-Metal / server-metal (GPUx1) (push) Has been cancelled Details Server-Metal / server-metal (GPUx1, backend-sampling) (push) Has been cancelled Details Server / server (RelWithDebInfo, ADDRESS) (push) Has been cancelled Details Server / server (RelWithDebInfo, UNDEFINED) (push) Has been cancelled Details Server / server (Release, , ) (push) Has been cancelled Details Server / server (Release, LLAMA_ARG_BACKEND_SAMPLING=1, ) (push) Has been cancelled Details Server / server-windows (push) Has been cancelled Details CI / macOS-latest-swift (generic/platform=iOS) (push) Has been cancelled Details CI / macOS-latest-swift (generic/platform=macOS) (push) Has been cancelled Details CI / macOS-latest-swift (generic/platform=tvOS) (push) Has been cancelled Details Release / release (push) Has been cancelled Details Close inactive issues / close-issues (push) Has been cancelled Details Publish Docker image / Push Docker image to Docker Hub (map[cuda_version:12.4.0 dockerfile:.devops/cuda.Dockerfile free_disk_space:true full:true light:true platforms:linux/amd64 runs_on:ubuntu-22.04 server:true tag:cuda cuda12 ubuntu_version:22.04]) (push) Has been cancelled Details Publish Docker image / Push Docker image to Docker Hub (map[cuda_version:13.1.0 dockerfile:.devops/cuda-new.Dockerfile free_disk_space:true full:true light:true platforms:linux/amd64 runs_on:ubuntu-22.04 server:true tag:cuda13 ubuntu_version:24.04]) (push) Has been cancelled Details Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/cpu.Dockerfile free_disk_space:false full:true light:true platforms:linux/amd64 runs_on:ubuntu-22.04 server:true tag:cpu]) (push) Has been cancelled Details Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/intel.Dockerfile free_disk_space:true full:true light:true platforms:linux/amd64 runs_on:ubuntu-22.04 server:true tag:intel]) (push) Has been cancelled Details Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/musa.Dockerfile free_disk_space:true full:true light:true platforms:linux/amd64 runs_on:ubuntu-22.04 server:true tag:musa]) (push) Has been cancelled Details Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/rocm.Dockerfile free_disk_space:true full:true light:true platforms:linux/amd64 runs_on:ubuntu-22.04 server:true tag:rocm]) (push) Has been cancelled Details Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/s390x.Dockerfile free_disk_space:false full:true light:true platforms:linux/s390x runs_on:ubuntu-22.04-s390x server:true tag:s390x]) (push) Has been cancelled Details Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/vulkan.Dockerfile free_disk_space:false full:true light:true platforms:linux/amd64 runs_on:ubuntu-22.04 server:true tag:vulkan]) (push) Has been cancelled Details Publish Docker image / Create and push git tag (push) Has been cancelled Details Update Winget Package / Update Winget Package (push) Has been cancelled Details	2026-03-13 20:56:10 +01:00
Piotr Wilkin (ilintar)	acb7c79069	common/parser: handle reasoning budget (#20297 ) * v1 * Finished! * Handlie cli * Reasoning sampler * Apply suggestions from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Less explosive terminology :) * Add utf-8 case and tests * common : migrate reasoning budget sampler to common * cont : clean up * cont : expose state and allow passing as initial state * cont : remove unused imports * cont : update state machine doc string --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> Co-authored-by: Alde Rojas <hello@alde.dev>	2026-03-11 10:26:12 +01:00
Aldehir Rojas	c96f608d98	common: consolidate PEG string parsers (#20263 ) Copilot Setup Steps / copilot-setup-steps (push) Has been cancelled Details Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Has been cancelled Details Python check requirements.txt / check-requirements (push) Has been cancelled Details Python Type-Check / pyright type-check (push) Has been cancelled Details Update Operations Documentation / update-ops-docs (push) Has been cancelled Details * common : consolidate PEG string parsers * cont : fix json_string_content()	2026-03-10 00:29:21 +01:00
Piotr Wilkin (ilintar)	62b8143ad2	Fix structured outputs (#20223 ) Copilot Setup Steps / copilot-setup-steps (push) Has been cancelled Details Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Has been cancelled Details Python check requirements.txt / check-requirements (push) Has been cancelled Details Python Type-Check / pyright type-check (push) Has been cancelled Details Update Operations Documentation / update-ops-docs (push) Has been cancelled Details * Fix structured outputs * Update common/chat-auto-parser-generator.cpp Co-authored-by: Aldehir Rojas <hello@alde.dev> --------- Co-authored-by: Aldehir Rojas <hello@alde.dev>	2026-03-08 17:14:43 +01:00
Piotr Wilkin (ilintar)	c024d85908	Autoparser: True streaming (#20177 ) Copilot Setup Steps / copilot-setup-steps (push) Has been cancelled Details Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Has been cancelled Details Python check requirements.txt / check-requirements (push) Has been cancelled Details Python Type-Check / pyright type-check (push) Has been cancelled Details Update Operations Documentation / update-ops-docs (push) Has been cancelled Details * Relax atomicity constraint for nicer, more pleasent, True Streaming parsing * Whitespace * Remove redundant atomics	2026-03-07 01:55:33 +01:00
Piotr Wilkin (ilintar)	2f2923f895	Autoparser: add optional argument reshuffle capability (#20171 ) Copilot Setup Steps / copilot-setup-steps (push) Has been cancelled Details Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Has been cancelled Details Python check requirements.txt / check-requirements (push) Has been cancelled Details Python Type-Check / pyright type-check (push) Has been cancelled Details Update Operations Documentation / update-ops-docs (push) Has been cancelled Details * Allow reshuffled arguments in tagged argument parser format tool calls. * Remove shuffle just keep the optional parsers in any order * Remove unnecessary import	2026-03-06 22:34:15 +01:00
Piotr Wilkin (ilintar)	566059a26b	Autoparser - complete refactoring of parser architecture (#18675 ) Copilot Setup Steps / copilot-setup-steps (push) Has been cancelled Details Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Has been cancelled Details Python check requirements.txt / check-requirements (push) Has been cancelled Details Python Type-Check / pyright type-check (push) Has been cancelled Details Update Operations Documentation / update-ops-docs (push) Has been cancelled Details * Autoparser - full single commit squish * Final pre-merge changes: minor fixes, Kimi 2.5 model parser	2026-03-06 21:01:00 +01:00

11 Commits