Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
13,009 workflow run results
13,009 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

SYCL: Reduce most of the compiler warnings Pull Request Labeler #6107: Pull request #10748 opened by qnixsynapse
21s
21s
Publish Docker image Publish Docker image #14776: Scheduled
31m 51s master
master
31m 51s
vulkan: dynamic subgroup size for the remaining k quants Server #8840: Pull request #10745 opened by netrunnereve
4m 34s vulkan2
vulkan2
4m 34s
vulkan: dynamic subgroup size for the remaining k quants CI #17451: Pull request #10745 opened by netrunnereve
21m 9s vulkan2
vulkan2
21m 9s
vulkan: dynamic subgroup size for the remaining k quants EditorConfig Checker #19521: Pull request #10745 opened by netrunnereve
19s vulkan2
vulkan2
19s
vulkan: dynamic subgroup size for the remaining k quants Pull Request Labeler #6106: Pull request #10745 opened by netrunnereve
16s
16s
add verbosity -1 to log token, so can output only tokens with -lv -1 CI #17450: Pull request #10744 opened by YannFollet
31m 22s YannFollet:log-verbosity-token-only
YannFollet:log-verbosity-token-only
31m 22s
add verbosity -1 to log token, so can output only tokens with -lv -1 Server #8839: Pull request #10744 opened by YannFollet
6m 14s YannFollet:log-verbosity-token-only
YannFollet:log-verbosity-token-only
6m 14s
add verbosity -1 to log token, so can output only tokens with -lv -1 EditorConfig Checker #19520: Pull request #10744 opened by YannFollet
22s YannFollet:log-verbosity-token-only
YannFollet:log-verbosity-token-only
22s
add verbosity -1 to log token, so can output only tokens with -lv -1 Pull Request Labeler #6105: Pull request #10744 opened by YannFollet
16s
16s
Cuda build doc EditorConfig Checker #19519: Pull request #10743 opened by YannFollet
20s YannFollet:cuda-build-doc
YannFollet:cuda-build-doc
20s
Cuda build doc Pull Request Labeler #6104: Pull request #10743 opened by YannFollet
15s
15s
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars Pull Request Labeler #6103: Pull request #9639 synchronize by ochafik
19s
19s
Close inactive issues Close inactive issues #269: Scheduled
31s master
master
31s
Opt class for positional argument handling EditorConfig Checker #19518: Pull request #10508 synchronize by ericcurtin
17s ericcurtin:new-style-run
ericcurtin:new-style-run
17s
Opt class for positional argument handling CI #17449: Pull request #10508 synchronize by ericcurtin
19m 24s ericcurtin:new-style-run
ericcurtin:new-style-run
19m 24s
Opt class for positional argument handling Server #8838: Pull request #10508 synchronize by ericcurtin
8m 35s ericcurtin:new-style-run
ericcurtin:new-style-run
8m 35s
Opt class for positional argument handling Pull Request Labeler #6102: Pull request #10508 synchronize by ericcurtin
13s
13s
server: Add timeout to stop the server automatically when idling for too long. Pull Request Labeler #6101: Pull request #10742 opened by Sumandora
15s
15s
more perfo with llamafile tinyblas on x86_64. EditorConfig Checker #19516: Pull request #10714 synchronize by Djip007
23s Djip007:perfo/tinyblas
Djip007:perfo/tinyblas
23s
more perfo with llamafile tinyblas on x86_64. Server #8836: Pull request #10714 synchronize by Djip007
5m 58s Djip007:perfo/tinyblas
Djip007:perfo/tinyblas
5m 58s
more perfo with llamafile tinyblas on x86_64. CI #17447: Pull request #10714 synchronize by Djip007
22m 12s Djip007:perfo/tinyblas
Djip007:perfo/tinyblas
22m 12s
more perfo with llamafile tinyblas on x86_64. Pull Request Labeler #6100: Pull request #10714 synchronize by Djip007
24s
24s
ggml-cpu: replace AArch64 NEON assembly with intrinsics in ggml_gemm_q4_0_4x4_q8_0() Pull Request Labeler #6099: Pull request #10624 synchronize by angt
14s
14s
CUDA: fix shared memory access condition for mmv (#10740) CI #17446: Commit 26a8406 pushed by JohannesGaessler
44m 9s master
master
44m 9s