Skip to content

Actions: ggml-org/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
14,278 workflow runs
14,278 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization Server #23420: Pull request #16653 synchronize by JohannesGaessler
Queued JohannesGaessler:llama-memory-fit-9
JohannesGaessler:llama-memory-fit-9
Queued
Mamba2 SSD Server #23419: Pull request #16982 synchronize by gabe-l-hart
Queued gabe-l-hart:Mamba2SSD
gabe-l-hart:Mamba2SSD
Queued
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization Server #23418: Pull request #16653 synchronize by JohannesGaessler
19m 45s JohannesGaessler:llama-memory-fit-9
JohannesGaessler:llama-memory-fit-9
19m 45s
webui: add "delete all conversations" button to import/export tab Server #23417: Pull request #17444 synchronize by thomasjfox
Action required thomasjfox:webui-delete-all-conversations
thomasjfox:webui-delete-all-conversations
Action required
cuda: optimize SOLVE_TRI using registers and FMAF Server #23416: Pull request #17703 synchronize by wsbagnsv1
Action required wsbagnsv1:TRI_SOLVE
wsbagnsv1:TRI_SOLVE
Action required
Add circular tiling support to pad, for Vulkan, CUDA, and CPU (used for making seamless textures) Server #23415: Pull request #16985 synchronize by Phylliida
Action required Phylliida:master
Phylliida:master
Action required
cuda: optimize SOLVE_TRI using registers and FMAF Server #23414: Pull request #17703 synchronize by wsbagnsv1
Action required wsbagnsv1:TRI_SOLVE
wsbagnsv1:TRI_SOLVE
Action required
mtmd: Add DeepSeekOCR Support Server #23413: Pull request #17400 synchronize by sfallah
Queued sfallah:sf/deepseek-ocr
sfallah:sf/deepseek-ocr
Queued
Add support for CUMSUM and TRI for CUDA. (#17584) Server #23412: Commit 96fe9ba pushed by pwilkin
Queued master
master
Queued
cuda: optimize SOLVE_TRI using registers and FMAF Server #23411: Pull request #17703 synchronize by wsbagnsv1
Action required wsbagnsv1:TRI_SOLVE
wsbagnsv1:TRI_SOLVE
Action required
docs(server): clarify that --ctx-size is total context divided among parallel slots Server #23410: Pull request #17767 opened by kitaekatt
Action required kitaekatt:docs/clarify-ctx-size-parallel
kitaekatt:docs/clarify-ctx-size-parallel
Action required
cuda: optimize SOLVE_TRI using registers and FMAF Server #23409: Pull request #17703 synchronize by wsbagnsv1
Action required wsbagnsv1:TRI_SOLVE
wsbagnsv1:TRI_SOLVE
Action required
metal : attach residency sets to queue Server #23408: Pull request #17766 synchronize by ggerganov
Queued gg/idle-new
gg/idle-new
Queued
metal : attach residency sets to queue Server #23407: Pull request #17766 opened by ggerganov
25s gg/idle-new
gg/idle-new
25s
cuda: optimize SOLVE_TRI using registers and FMAF Server #23406: Pull request #17703 synchronize by wsbagnsv1
Action required wsbagnsv1:TRI_SOLVE
wsbagnsv1:TRI_SOLVE
Action required
cuda: optimize SOLVE_TRI using registers and FMAF Server #23405: Pull request #17703 synchronize by wsbagnsv1
Action required wsbagnsv1:TRI_SOLVE
wsbagnsv1:TRI_SOLVE
Action required
ggml-zendnn : add ZenDNN backend for AMD CPUs Server #23404: Pull request #17690 synchronize by z-vishal
Action required z-vishal:ggml-zendnn
z-vishal:ggml-zendnn
Action required
Add a search field on model selector / improve mobile display Server #23403: Pull request #17765 opened by ServeurpersoCom
Queued ServeurpersoCom:models-search
ServeurpersoCom:models-search
Queued
ggml webgpu: unary op suppport, code refactoring, ops support Server #23402: Pull request #17764 opened by reeselevine
Queued reeselevine:master
reeselevine:master
Queued
sampling : add support for backend sampling Server #23401: Pull request #17004 synchronize by ggerganov
Queued danbev:gpu-sampling
danbev:gpu-sampling
Queued
metal: TRI, FILL, EXPM1, SOFTPLUS (#16623) Server #23400: Commit bde188d pushed by ggerganov
Queued master
master
Queued
CANN: Refactor is_matched_graph for better maintainability Server #23398: Pull request #17758 synchronize by rauletorresc
Queued rauletorresc:rauletorresc-patch-4
rauletorresc:rauletorresc-patch-4
Queued
metal: TRI, FILL, EXPM1, SOFTPLUS Server #23397: Pull request #16623 synchronize by gabe-l-hart
Queued gabe-l-hart:ggml-cumsum-tri
gabe-l-hart:ggml-cumsum-tri
Queued
ggml-hexagon: fix rope failure at test-backend-ops Server #23396: Pull request #17565 synchronize by chraac
Queued chraac:dev-fix-rope
chraac:dev-fix-rope
Queued
[WIP]ggml-hexagon: create generalized functions for cpu side op Server #23395: Pull request #17500 synchronize by chraac
Queued chraac:dev-hexagon-refactoring-part2
chraac:dev-hexagon-refactoring-part2
Queued