Skip to content

Actions: ngxson/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
1,189 workflow run results
1,189 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

CANN: Add SOC TYPE printing in cmake configuration (#13837) Server #1636: Commit 1e8659e pushed by ngxson
10m 8s master
master
10m 8s
opencl: add new ops - argsort, div, sub, addrows, sigmoid, … Server #1635: Commit a3c3084 pushed by ngxson
22m 12s master
master
22m 12s
opencl: mark mul_mat f32f32 as supporting non-contiguous tensors … Server #1634: Commit 1701d4c pushed by ngxson
10m 5s master
master
10m 5s
vulkan: use timestamp queries for GGML_VULKAN_PERF (#13817) Server #1633: Commit bef8176 pushed by ngxson
12m 22s master
master
12m 22s
cmake : add llama-cparams.cpp to build (#13832) Server #1632: Commit 34b7c04 pushed by ngxson
10m 23s master
master
10m 23s
SYCL: add gelu_erf kernel (#13749) Server #1631: Commit f3101a8 pushed by ngxson
9m 51s master
master
9m 51s
ggml : add ggml_repeat_4d (#13824) Server #1630: Commit a8ea03d pushed by ngxson
10m 13s master
master
10m 13s
ggml : riscv: add xtheadvector support (#13720) Server #1629: Commit 05f6ac6 pushed by ngxson
11m 26s master
master
11m 26s
mtmd : support Qwen 2.5 Omni (input audio+vision, no audio output) (#… Server #1628: Commit bc583e3 pushed by ngxson
10m 59s master
master
10m 59s
ggml-cpu: x86 feature detection is specific to x86 (#13811) Server #1627: Commit 7fe03e7 pushed by ngxson
20m 39s master
master
20m 39s
ggml : allow CUDA graphs when using pipeline parallelism (#13814) Server #1626: Commit 952f395 pushed by ngxson
10m 9s master
master
10m 9s
kv-cells : track min/max used cells and per-sequence positions (#13808) Server #1625: Commit 8171312 pushed by ngxson
15m 30s master
master
15m 30s
sampling : make sure samplers return at least 1 token (#13822) Server #1624: Commit f9cd683 pushed by ngxson
10m 7s master
master
10m 7s
Xsn/qwen25omni Server #1623: Pull request #25 synchronize by ngxson
10m 29s xsn/qwen25omni
xsn/qwen25omni
10m 29s
llama : validate seq id batch input (#13809) Server #1622: Commit 4f81b33 pushed by ngxson
11m 10s master
master
11m 10s
server: --offline mode (#13804) Server #1621: Commit cdf94a1 pushed by ngxson
11m 7s master
master
11m 7s
SYCL: Add non contiguous support in RMS_NORM and NORM kernels (#13611) Server #1620: Commit 6f180b9 pushed by ngxson
10m 34s master
master
10m 34s
server: fix streaming crashes (#13786) Server #1619: Commit 03f582a pushed by ngxson
10m 40s master
master
10m 40s
server: fix format of streamed tool call deltas (diff name, fix id … Server #1618: Commit d74e94c pushed by ngxson
10m 13s master
master
10m 13s
server: fix regression on streamed non-chat completion w/ stops (#13785) Server #1617: Commit f13847c pushed by ngxson
10m 34s master
master
10m 34s
examples : allow extracting embeddings from decoder contexts (#13797) Server #1616: Commit 79c137f pushed by ngxson
11m 0s master
master
11m 0s
llama : clarify deprecation message (#13794) Server #1615: Commit 2222931 pushed by ngxson
24m 33s master
master
24m 33s
Xsn/qwen25omni Server #1614: Pull request #25 synchronize by ngxson
11m 5s xsn/qwen25omni
xsn/qwen25omni
11m 5s
Xsn/qwen25omni Server #1613: Pull request #25 synchronize by ngxson
2m 25s xsn/qwen25omni
xsn/qwen25omni
2m 25s
Xsn/qwen25omni Server #1612: Pull request #25 synchronize by ngxson
9m 55s xsn/qwen25omni
xsn/qwen25omni
9m 55s