wmantly/llama.cpp-xrip
1
0 Fork 0
Code Issues Pull Requests Actions 32 Packages Projects Releases Wiki Activity
Files
master
llama.cpp-xrip/common
T
History
wmantly fa715571ea
build-cann.yml (push) Invalid workflow file
Details
CI (cpu) / ubuntu (x64, ubuntu-22.04) (push) Failing after 3m28s
Details
CI (cpu) / ubuntu (arm64, ubuntu-24.04-arm) (push) Canceled after 0s
Details
CI (CUDA, ubuntu) / hip (push) Failing after 3m3s
Details
CI (CUDA, ubuntu) / musa (push) Failing after 12s
Details
CI (3rd-party) / ubuntu-24-llguidance (push) Canceled after 0s
Details
CI (ibm) / ubuntu-26-s390x (VXE OFF) (push) Canceled after 0s
Details
CI (ibm) / ubuntu-26-s390x (VXE ON) (push) Canceled after 0s
Details
CI (ibm) / ubuntu-26-zdnn-s390x (push) Canceled after 0s
Details
CI (ibm) / ubuntu-24-ppc64le (push) Canceled after 0s
Details
CI (CUDA, ubuntu) / cuda (push) Canceled after 0s
Details
CI (self-hosted CUDA backend) / gpu-cuda (push) Canceled after 0s
Details
CI (self-hosted CUDA backend) / gpu-rocm (push) Canceled after 0s
Details
CI (self-hosted Metal backend) / gpu-metal (push) Canceled after 0s
Details
CI (self-hosted OpenVINO backend) / gpu-openvino-low-perf (push) Canceled after 0s
Details
CI (vulkan) / ubuntu-arm64 (push) Canceled after 0s
Details
CI (vulkan) / ubuntu-llvmpipe (push) Canceled after 0s
Details
CI (vulkan) / windows / arm64 (push) Canceled after 0s
Details
CI (vulkan) / windows / x64 (push) Canceled after 0s
Details
CI (self-hosted Vulkan backend) / gpu-vulkan-nvidia-cm (push) Canceled after 0s
Details
CI (self-hosted Vulkan backend) / gpu-vulkan-nvidia-cm2 (push) Canceled after 0s
Details
CI (self-hosted Vulkan backend) / gpu-vulkan-apple (push) Canceled after 0s
Details
CI (self-hosted Vulkan backend) / gpu-vulkan-intel-linux (push) Canceled after 0s
Details
CI (self-hosted Vulkan backend) / gpu-vulkan-intel-windows (push) Canceled after 0s
Details
Code Style Checker / model-naming (push) Canceled after 0s
Details
Server (sanitize) / server (RelWithDebInfo, ADDRESS) (push) Canceled after 0s
Details
Server (sanitize) / server (RelWithDebInfo, UNDEFINED) (push) Canceled after 0s
Details
CI (self-hosted KleidiAI backend) / cpu-arm64-graviton4-kleidiai (push) Canceled after 0s
Details
Server / ubuntu (push) Canceled after 0s
Details
Server / windows (push) Canceled after 0s
Details
CI (android) / default (push) Canceled after 0s
Details
CI (android) / ndk (push) Canceled after 0s
Details
CI (android) / arm64 (push) Canceled after 0s
Details
CI (opencl) / windows-2025-opencl-adreno (push) Canceled after 0s
Details
CI (riscv) / ubuntu-cpu-riscv64-native (push) Canceled after 0s
Details
CI (sycl) / ubuntu-24-sycl (fp16, ON) (push) Canceled after 0s
Details
CI (sycl) / ubuntu-24-sycl (fp32, OFF) (push) Canceled after 0s
Details
CI (sycl) / windows-latest-sycl (push) Canceled after 0s
Details
CI (wasm) / ubuntu-webgpu (push) Canceled after 0s
Details
Behavior Check / ubuntu (push) Canceled after 0s
Details
Behavior Check / windows (push) Canceled after 0s
Details
CI (apple) / macos-latest-arm64 (push) Canceled after 0s
Details
Build relocatable cmake package / linux (push) Canceled after 0s
Details
CI (cpu) / build-cmake-pkg (push) Canceled after 0s
Details
CI (cpu) / windows / arm64 (push) Canceled after 0s
Details
CI (cpu) / windows / x64-cpu-static (push) Canceled after 0s
Details
CI (cpu) / windows / x64-openblas (push) Canceled after 0s
Details
CI (sanitize) / ctest ([self-hosted X64 Linux CPU], UNDEFINED) (push) Canceled after 0s
Details
CI (sanitize) / ctest (ubuntu-24.04, ADDRESS) (push) Canceled after 0s
Details
CI (sanitize) / ctest (ubuntu-24.04, THREAD) (push) Canceled after 0s
Details
CI (openvino) / ubuntu-24-openvino (push) Canceled after 0s
Details
CI (openvino) / openvino-windows-2022 (push) Canceled after 0s
Details
CI (wasi) / ubuntu-webgpu (push) Canceled after 0s
Details
CI (self-hosted CPU backend) / cpu-x64-high-perf (push) Canceled after 0s
Details
CI (self-hosted CPU backend) / cpu-arm64-high-perf-graviton4 (push) Canceled after 0s
Details
EditorConfig Checker / editorconfig (push) Canceled after 0s
Details
Server (self-hosted) / server-metal (push) Canceled after 0s
Details
Server (self-hosted) / server-cuda (push) Canceled after 0s
Details
Server (self-hosted) / server-kleidiai (push) Canceled after 0s
Details
CI (virtgpu) / ubuntu-24-virtgpu (push) Canceled after 0s
Details
CI (self-hosted WebGPU backend) / gpu-webgpu-nvidia (push) Canceled after 0s
Details
CI (self-hosted WebGPU backend) / gpu-webgpu-apple (push) Canceled after 0s
Details
Release / check-release (push) Canceled after 0s
Details
Release / macos-cpu (arm64, arm64, -DGGML_METAL_EMBED_LIBRARY=ON -DCMAKE_OSX_DEPLOYMENT_TARGET=13.3, macos-26) (push) Canceled after 0s
Details
Release / macos-cpu (x64, x64, -DGGML_METAL=OFF -DCMAKE_OSX_DEPLOYMENT_TARGET=13.3, macos-15-intel) (push) Canceled after 0s
Details
Release / ubuntu-cpu (26.04-s390x, ubuntu-26.04-s390x) (push) Canceled after 0s
Details
Release / ubuntu-cpu (arm64, ubuntu-24.04-arm) (push) Canceled after 0s
Details
Release / ubuntu-cpu (s390x, ubuntu-24.04-s390x) (push) Canceled after 0s
Details
Release / ubuntu-cpu (x64, ubuntu-22.04) (push) Canceled after 0s
Details
Release / ubuntu-vulkan (arm64, ubuntu-24.04-arm) (push) Canceled after 0s
Details
Release / ubuntu-vulkan (x64, ubuntu-22.04) (push) Canceled after 0s
Details
Release / ubuntu-cuda (13.4, arm64) (push) Canceled after 0s
Details
Release / ubuntu-cuda (12.8, x64) (push) Canceled after 0s
Details
Release / ubuntu-cuda (13.4, x64) (push) Canceled after 0s
Details
Release / android-arm64 (push) Canceled after 0s
Details
Release / android-arm64-snapdragon (push) Canceled after 0s
Details
Release / linux-arm64-snapdragon (push) Canceled after 0s
Details
Release / ubuntu-24-openvino (push) Canceled after 0s
Details
Release / windows-openvino (push) Canceled after 0s
Details
Release / windows-cpu / arm64 (push) Canceled after 0s
Details
Release / windows-cpu / x64 (push) Canceled after 0s
Details
Release / windows-rocm (10.0.0, x64, gfx1010;gfx1011;gfx1012;gfx1030;gfx1031;gfx1032;gfx1033;gfx1034;gfx1035;gfx1036;gfx1100;gfx1101;gfx1102;gfx1103;gfx1150;gfx1151;gfx1152;gfx1153;gfx1200;gfx1201) (push) Canceled after 0s
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) Canceled after 0s
Details
Release / windows (arm64, vulkan, -G "Ninja Multi-Config" -DGGML_VULKAN=ON -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake, ggml-vulkan) (push) Canceled after 0s
Details
Release / windows (x64, vulkan, -DGGML_VULKAN=ON, ggml-vulkan) (push) Canceled after 0s
Details
Release / windows-cuda (13.4, arm64) (push) Canceled after 0s
Details
Release / windows-cuda (12.4, x64) (push) Canceled after 0s
Details
Release / windows-cuda (13.4, x64) (push) Canceled after 0s
Details
Release / windows-sycl (push) Canceled after 0s
Details
Release / ubuntu-24-sycl (fp16, ON) (push) Canceled after 0s
Details
Release / ubuntu-24-sycl (fp32, OFF) (push) Canceled after 0s
Details
Release / ubuntu-24-rocm (10.0.0, x64, gfx908;gfx90a;gfx942;gfx950;gfx1010;gfx1011;gfx1012;gfx1030;gfx1031;gfx1032;gfx1033;gfx1034;gfx1035;gfx1036;gfx1100;gfx1101;gfx1102;gfx1103;gfx1150;gfx1151;gfx1152;gfx1200;gfx1201) (push) Canceled after 0s
Details
Release / ubuntu-26-zdnn (push) Canceled after 0s
Details
Release / ios-xcode (push) Canceled after 0s
Details
Release / ui-build (push) Canceled after 0s
Details
common: load backends before parsing mmproj-device
2026-11-04 20:29:27 +00:00
..
jinja
server: expose the reasoning effort levels of the chat template (#31271)
2026-10-27 22:39:37 +01:00
parsers
chat : strip the think block in the qwen3-coder with reasoning_format none (#31380)
2026-10-30 22:38:04 -05:00
arg.cpp
common: load backends before parsing mmproj-device
2026-11-04 20:29:27 +00:00
arg.h
server : improve startup log messages (#29125)
2026-09-19 15:37:13 +03:00
base64.hpp
llava : expose as a shared library for downstream projects (#3613)
2023-11-07 00:36:23 +03:00
build-info.cpp.in
common : make build info output stream configurable (#28322)
2026-09-04 09:13:20 +03:00
build-info.h
common : make build info output stream configurable (#28322)
2026-09-04 09:13:20 +03:00
chat-auto-parser-generator.cpp
chat: replace output string with parts (#30389)
2026-10-14 01:03:56 +02:00
chat-auto-parser-helpers.cpp
chat: replace output string with parts (#30389)
2026-10-14 01:03:56 +02:00
chat-auto-parser-helpers.h
chat : avoid including json in chat.h (#21306)
2026-04-03 09:07:59 +03:00
chat-auto-parser.h
common: add json.h abstraction (#27511)
2026-08-22 16:28:28 +02:00
chat-diff-analyzer.cpp
common: add json.h abstraction (#27511)
2026-08-22 16:28:28 +02:00
chat-peg-parser.cpp
chat : name tool and argument parser rules by index (#30088)
2026-10-07 22:37:51 +02:00
chat-peg-parser.h
common: add json.h abstraction (#27511)
2026-08-22 16:28:28 +02:00
chat.cpp
chat : stop qwen3-coder reasoning and content before template separators (#30557)
2026-10-28 10:11:47 +02:00
chat.h
server: expose the reasoning effort levels of the chat template (#31271)
2026-10-27 22:39:37 +01:00
CMakeLists.txt
common : allow concurrent downloads across processes (#29312)
2026-10-23 23:52:56 +02:00
common.cpp
Merge upstream master; take upstream DFlash2, MMQ fusion, and top-k
2026-11-01 22:29:01 +03:00
common.h
common : delete fs_path_to_utf8() (#31423)
2026-10-30 16:20:04 +01:00
console.cpp
cli: exit on stdin EOF and drop the console wide Ctrl+C broadcast (#29722)
2026-09-30 16:24:46 +02:00
console.h
cli : add command and file auto-completion (#19985)
2026-03-05 10:47:28 +01:00
debug.cpp
common: fix missing exports in llama-common (#22340)
2026-04-27 08:06:39 +03:00
debug.h
common: fix missing exports in llama-common (#22340)
2026-04-27 08:06:39 +03:00
download.cpp
common : delete fs_path_to_utf8() (#31423)
2026-10-30 16:20:04 +01:00
download.h
common : allow concurrent downloads across processes (#29312)
2026-10-23 23:52:56 +02:00
file-lock.cpp
common : allow concurrent downloads across processes (#29312)
2026-10-23 23:52:56 +02:00
file-lock.h
common : allow concurrent downloads across processes (#29312)
2026-10-23 23:52:56 +02:00
fit.cpp
server: add router device memory margin parameter for dynamic unloading (#21231)
2026-10-27 12:14:42 +01:00
fit.h
server: add router device memory margin parameter for dynamic unloading (#21231)
2026-10-27 12:14:42 +01:00
hf-cache.cpp
common : delete fs_path_to_utf8() (#31423)
2026-10-30 16:20:04 +01:00
hf-cache.h
common : allow concurrent downloads across processes (#29312)
2026-10-23 23:52:56 +02:00
http.h
common: honor HTTP_PROXY/HTTPS_PROXY env vars in http client (#21752)
2026-10-16 17:01:37 +02:00
imatrix-loader.cpp
imatrix: calculate activation-based statistics for new format (GGUF) imatrices (#14891)
2026-10-04 11:24:53 +02:00
imatrix-loader.h
imatrix: calculate activation-based statistics for new format (GGUF) imatrices (#14891)
2026-10-04 11:24:53 +02:00
json-schema-to-grammar.cpp
common, grammar: add recursive depth limit, make it a requirement (#31153)
2026-10-25 23:53:08 +01:00
json-schema-to-grammar.h
common, grammar: add recursive depth limit, make it a requirement (#31153)
2026-10-25 23:53:08 +01:00
json-schema.cpp
common, grammar: add recursive depth limit, make it a requirement (#31153)
2026-10-25 23:53:08 +01:00
json-schema.h
common : implement common_schema internal representation for JSON schemas (#28736)
2026-09-12 16:14:50 -05:00
json.cpp
common: json.h: fix clang lto (#27575)
2026-08-23 01:11:10 +02:00
json.h
json: Fixed json enum handling (#28518)
2026-09-21 10:32:07 +02:00
llguidance.cpp
llama : support multi-output backend sampling (#25532)
2026-08-10 16:58:56 +03:00
log.cpp
tests : consolidate context state tests into test-llama-context (#30023)
2026-10-13 16:21:55 +03:00
log.h
tests : consolidate context state tests into test-llama-context (#30023)
2026-10-13 16:21:55 +03:00
ngram-cache.cpp
common : read ngram cache parts by reference instead of copying (#30061)
2026-10-16 10:06:32 +03:00
ngram-cache.h
spec : add self‑speculative decoding (no draft model required) + refactor (#18471)
2026-01-28 19:42:42 +02:00
ngram-map.cpp
speculative : fix out-of-bounds read in ngram-map on prompt shrink (#23936)
2026-07-07 10:25:04 +03:00
ngram-map.h
fix: correct misspellings in code comments (#21217)
2026-03-31 13:50:51 +02:00
ngram-mod.cpp
ngram-mod : Add missing include (#23857)
2026-05-29 09:21:37 +03:00
ngram-mod.h
ngram-mod : fix build [no ci] (#19216)
2026-01-30 21:27:27 +02:00
peg-parser.cpp
chat : stop qwen3-coder reasoning and content before template separators (#30557)
2026-10-28 10:11:47 +02:00
peg-parser.h
chat : stop qwen3-coder reasoning and content before template separators (#30557)
2026-10-28 10:11:47 +02:00
preset.cpp
common : delete fs_path_to_utf8() (#31423)
2026-10-30 16:20:04 +01:00
preset.h
common : use fs::path for config dir (#29649)
2026-09-29 17:22:49 +02:00
reasoning-budget.cpp
common : end reasoning budget forcing on an end tag from the prompt (#31374)
2026-10-29 19:27:50 -05:00
reasoning-budget.h
common : add support for multiple end sequences in the reasoning budget sampler (#25544)
2026-07-25 11:58:09 +02:00
sampling.cpp
llama : report compute graph reallocations during inference (#30329)
2026-10-12 11:53:58 +03:00
sampling.h
chat : refactor API (#30210)
2026-10-09 10:06:22 -05:00
speculative.cpp
Merge upstream master; take upstream DFlash2, MMQ fusion, and top-k
2026-11-01 22:29:01 +03:00
speculative.h
Merge upstream master; take upstream DFlash2, MMQ fusion, and top-k
2026-11-01 22:29:01 +03:00
subproc.cpp
common: add subproc.h wrapper, disabled on android/ios (#26102)
2026-07-26 20:54:25 +02:00
subproc.h
common: add subproc.h wrapper, disabled on android/ios (#26102)
2026-07-26 20:54:25 +02:00
trie.cpp
common : add support for multiple end sequences in the reasoning budget sampler (#25544)
2026-07-25 11:58:09 +02:00
trie.h
common : add support for multiple end sequences in the reasoning budget sampler (#25544)
2026-07-25 11:58:09 +02:00
unicode.cpp
common/peg : handle invalid utf-8 sequences in the AST (#29161)
2026-09-20 06:51:40 -05:00
unicode.h
common/peg : handle invalid utf-8 sequences in the AST (#29161)
2026-09-20 06:51:40 -05:00
win-app.manifest
cmake : embed an app manifest in all Windows exes (#31329)
2026-10-30 10:56:53 +01:00