Skip to content

Actions: EAddario/llama.cpp

Actions

CI (cpu)

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build-cpu.yml
89 workflow runs
89 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
chat : add dedicated Ling 3.0 (Bailing V3) parser (#28682) CI (cpu) #89: Commit 59657a6 pushed by EAddario
1d 0h 0m 1s master
master
1d 0h 0m 1s
hexagon: enable I32 GET_ROWS (#29116) CI (cpu) #88: Commit e613ef2 pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
metal : fix FA support checks (#29122) CI (cpu) #87: Commit 60b06ab pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
hexagon: add ROLL op support (#29105) CI (cpu) #86: Commit 2b18470 pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
ggml-cpu: add F16 input to the FWHT (#27779) CI (cpu) #85: Commit 4fea119 pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
cmake : skip PCH for llama-server PCH when using MSVC (#28763) CI (cpu) #84: Commit 8ea2902 pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
tests: tolerate a shared pool abort in test_completion_unified (#28759) CI (cpu) #83: Commit 8172e65 pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
opencl: add A8 Q4_0 mm binary kernel support (#28268) CI (cpu) #82: Commit df03399 pushed by EAddario
1d 0h 0m 3s master
master
1d 0h 0m 3s
spec: fix failed to decode mtmd chunk with DFlash (#28587) CI (cpu) #81: Commit fa67698 pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
vulkan : add command-buffer debug labels for GPU profilers (#28101) CI (cpu) #80: Commit 72797e8 pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
vulkan: use spec constant for matrix matrix multiplication A-type (#2… CI (cpu) #79: Commit 91f6a6c pushed by EAddario
1d 0h 0m 1s master
master
1d 0h 0m 1s
vulkan: add dedicated iq4_xs mat-vec shader (#28426) CI (cpu) #78: Commit df750f7 pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
llama: disable lazy tensor loading by default on iGPUs (#28326) CI (cpu) #77: Commit f3f1a8f pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
spec: single device drafter should create meta backend wrapper (#28390) CI (cpu) #76: Commit 415e909 pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
llama : add missing headers (#28566) CI (cpu) #75: Commit ca86fb2 pushed by EAddario
1d 0h 0m 3s master
master
1d 0h 0m 3s
Revert "CUDA: size routed MoE MMQ N-tiles from typical expert width o… CI (cpu) #74: Commit e71b805 pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
common: add --log-jsonl (#28437) CI (cpu) #73: Commit 7620399 pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
ggml : replace compile definitions with version.h.in (#28364) CI (cpu) #72: Commit 86b351f pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
convert : skip bias_vl tensor in DeepSeek-V4 DSpark conversion (#28294) CI (cpu) #71: Commit d646c9d pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
sycl: reduce redundant work in Q4_K multi-column MMVQ (#27062) CI (cpu) #70: Commit 4aa6ffb pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
qwen4exp: support recurrent state rollback (#28123) CI (cpu) #69: Commit 0eadefe pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
sycl: make --fit respect --fit-target better (#27629) CI (cpu) #68: Commit cc83d7b pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
Vulkan: add hoisting support for row IDs and expert count in shaders … CI (cpu) #67: Commit 90c26fc pushed by EAddario
1d 0h 0m 3s master
master
1d 0h 0m 3s
context : disable non-fused GDN and LID ops (#27877) CI (cpu) #66: Commit 8663224 pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s
tests : run test-save-load-state across all architectures (#27755) CI (cpu) #65: Commit 4e97ac8 pushed by EAddario
1d 0h 0m 2s master
master
1d 0h 0m 2s