Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
4,700 workflow run results
4,700 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

server : include speculative decoding stats when timings_per_token is… CI #20727: Commit 5d01670 pushed by ggerganov
54m 47s master
master
54m 47s
llamafile : ppc64le GEMV forwarding for FP32. (#12594) CI #20725: Commit 1373176 pushed by ggerganov
50m 11s master
master
50m 11s
rpc : send hash when tensor data is above some fixed threshold (#12496) CI #20724: Commit ab6ab8f pushed by rgerganov
47m 16s master
master
47m 16s
llamafile : ppc64le GEMV forwarding for FP32. CI #20722: Pull request #12594 synchronize by amritahs-ibm
38m 3s amritahs-ibm:FP32_MMA_Batch1
amritahs-ibm:FP32_MMA_Batch1
38m 3s
llamafile : ppc64le GEMV forwarding for FP32. CI #20721: Pull request #12594 synchronize by amritahs-ibm
7m 23s amritahs-ibm:FP32_MMA_Batch1
amritahs-ibm:FP32_MMA_Batch1
7m 23s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp CI #20720: Pull request #12326 synchronize by jeffzhou2000
46m 29s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
46m 29s
musa: fix all warnings, re-enable -DLLAMA_FATAL_WARNINGS=ON in ci and update doc CI #20719: Pull request #12611 synchronize by yeahdongcn
45m 38s makllama:xd/warnings_musa
makllama:xd/warnings_musa
45m 38s
server: streaming of tool calls and thoughts when --jinja is on CI #20718: Pull request #12379 synchronize by ochafik
42m 8s ochafik:tool-diffs
ochafik:tool-diffs
42m 8s
server : Support listening on a unix socket (#12613) CI #20717: Commit 2099a9d pushed by ngxson
52m 36s master
master
52m 36s
Include speculative decoding stats when timings_per_token is enabled CI #20716: Pull request #12603 reopened by mostlygeek
51m 41s mostlygeek:master
mostlygeek:master
51m 41s
Include speculative decoding stats when timings_per_token is enabled CI #20715: Pull request #12603 synchronize by mostlygeek
1m 4s mostlygeek:master
mostlygeek:master
1m 4s
Include speculative decoding stats when timings_per_token is enabled CI #20714: Pull request #12603 synchronize by mostlygeek
31m 1s mostlygeek:master
mostlygeek:master
31m 1s
ci: add Linux cross-compile build CI #20713: Pull request #12428 synchronize by bandoti
40m 18s bandoti:ci-build-cross
bandoti:ci-build-cross
40m 18s
ci: add Linux cross-compile build CI #20712: Pull request #12428 synchronize by bandoti
2m 20s bandoti:ci-build-cross
bandoti:ci-build-cross
2m 20s
llama : fix non-causal mask for gemma 3 CI #20711: Pull request #12615 synchronize by ngxson
45m 9s ngxson:xsn/llama_set_attn_type
ngxson:xsn/llama_set_attn_type
45m 9s
llama : fix non-causal mask for gemma 3 CI #20710: Pull request #12615 opened by ngxson
4m 40s ngxson:xsn/llama_set_attn_type
ngxson:xsn/llama_set_attn_type
4m 40s
metal : improve FA + improve MoE CI #20709: Pull request #12612 synchronize by ggerganov
1h 7m 3s gg/metal-fa-diff-heads
gg/metal-fa-diff-heads
1h 7m 3s
server : Support listening on a unix socket CI #20708: Pull request #12613 synchronize by p1-0tr
56m 14s p1-0tr:ps-server-af-unix
p1-0tr:ps-server-af-unix
56m 14s
metal : improve FA + improve MoE CI #20706: Pull request #12612 synchronize by ggerganov
51m 32s gg/metal-fa-diff-heads
gg/metal-fa-diff-heads
51m 32s
metal : improve FA + improve MoE CI #20705: Pull request #12612 opened by ggerganov
1m 28s gg/metal-fa-diff-heads
gg/metal-fa-diff-heads
1m 28s
opencl: add multi and vision rope, gelu_quick and im2col (#12600) CI #20704: Commit 5dec47d pushed by max-krasnyansky
54m 14s master
master
54m 14s
ci: add Linux cross-compile build CI #20703: Pull request #12428 synchronize by bandoti
3m 29s bandoti:ci-build-cross
bandoti:ci-build-cross
3m 29s
musa: fix all warnings, re-enable -DLLAMA_FATAL_WARNINGS=ON in ci and update doc CI #20702: Pull request #12611 opened by yeahdongcn
1h 0m 37s makllama:xd/warnings_musa
makllama:xd/warnings_musa
1h 0m 37s
ci: add Linux cross-compile build CI #20701: Pull request #12428 synchronize by bandoti
29m 15s bandoti:ci-build-cross
bandoti:ci-build-cross
29m 15s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp CI #20700: Pull request #12326 synchronize by jeffzhou2000
52m 42s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
52m 42s