Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

Actions: ggml-org/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
12,571 workflow runs
12,571 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml : fix SpaceMit IME array out-of-bounds in task assignment (#16629) Server #20402: Commit 342c728 pushed by ggerganov
37m 23s master
master
37m 23s
vulkan: Add State Space Model (SSM) Operations Support Server #20401: Pull request #16463 synchronize by giuseppe
44m 17s giuseppe:ssm-vulkan
giuseppe:ssm-vulkan
44m 17s
webui: reorganize settings layout (#16607) Server #20400: Commit ababae7 pushed by allozaur
1h 37m 45s master
master
1h 37m 45s
webui: add OAI-Compat Harmony tool-call streaming visualization and persistence in chat UI Server #20399: Pull request #16618 synchronize by ServeurpersoCom
1h 6m 18s ServeurpersoCom:harmony-toolcall-debug-option
ServeurpersoCom:harmony-toolcall-debug-option
1h 6m 18s
rpc : report actual free memory Server #20398: Pull request #16616 synchronize by rgerganov
2h 6m 52s rgerganov:rpc-track-mem
rgerganov:rpc-track-mem
2h 6m 52s
vulkan: fix debug build (add_rms_len/data not found) (#16624) Server #20397: Commit b194915 pushed by 0cc4m
2h 31m 27s master
master
2h 31m 27s
CUDA: fuse gate + up for mmvq, and mmvf Server #20396: Pull request #16630 synchronize by am17an
2h 17m 47s am17an:cuda_fuse_gate
am17an:cuda_fuse_gate
2h 17m 47s
CUDA: fuse gate + up for mmvq, and mmvf Server #20395: Pull request #16630 synchronize by am17an
4m 14s am17an:cuda_fuse_gate
am17an:cuda_fuse_gate
4m 14s
Add experimental ggml-hexagon backend for the Hexagon NPU Server #20394: Pull request #16547 synchronize by max-krasnyansky
2h 2m 26s CodeLinaro:hexagon
CodeLinaro:hexagon
2h 2m 26s
CUDA: fuse gate + up for mmvq, and mmvf Server #20393: Pull request #16630 opened by am17an
28m 11s am17an:cuda_fuse_gate
am17an:cuda_fuse_gate
28m 11s
Add experimental ggml-hexagon backend for the Hexagon NPU Server #20392: Pull request #16547 synchronize by max-krasnyansky
34m 0s CodeLinaro:hexagon
CodeLinaro:hexagon
34m 0s
metal : add CONV_TRANSPOSE_2D (#16542) Server #20391: Commit 9ad4f19 pushed by ggerganov
3h 7m 46s master
master
3h 7m 46s
grammar : use int64_t to avoid int overflows in int schema to grammar… Server #20390: Commit 79967ec pushed by ggerganov
36m 23s master
master
36m 23s
ggml : fix SpaceMit IME array out-of-bounds in task assignment Server #20389: Pull request #16629 opened by muggle-stack
1h 6m 46s muggle-stack:fix/spacemit-ime-array-bounds
muggle-stack:fix/spacemit-ime-array-bounds
1h 6m 46s
webui: reorganize settings layout Server #20388: Pull request #16607 synchronize by ServeurpersoCom
20m 14s ServeurpersoCom:settings-layout
ServeurpersoCom:settings-layout
20m 14s
SYCL SET operator optimized for F32 tensors (#16350) Server #20387: Commit ceff6bb pushed by NeoZhangJianyu
31m 58s master
master
31m 58s
fix: use int64_t to avoid overflows in int schema to grammar conversion Server #20386: Pull request #16626 opened by ochafik
28m 33s ochafik:fix-int64-overflow
ochafik:fix-int64-overflow
28m 33s
extend server/public_simplechat with simple minded interactive browser-client side based toolcalling - base logic Server #20385: Pull request #16563 synchronize by hanishkvc
Action required hanishkvc:hkvc_server_simplechat_toolcalling_v0400
hanishkvc:hkvc_server_simplechat_toolcalling_v0400
Action required
model : add BailingMoeV2 support Server #20384: Pull request #16063 synchronize by CISC
26m 46s cisc/bailingmoe2
cisc/bailingmoe2
26m 46s
opencl: transposed gemm/gemv moe kernel with mxfp4,f32 Server #20383: Pull request #16602 synchronize by shawngu-quic
Action required CodeLinaro:moe-mxfp4-trans-reorder
CodeLinaro:moe-mxfp4-trans-reorder
Action required
vulkan: fix debug build (add_rms_len/data not found) Server #20382: Pull request #16624 opened by jeffbolznv
31m 33s jeffbolznv:add_rms_debug
jeffbolznv:add_rms_debug
31m 33s
ggml: CUMSUM and TRI (CPU, Metal, CUDA) Server #20381: Pull request #16623 opened by gabe-l-hart
32m 35s gabe-l-hart:ggml-cumsum-tri
gabe-l-hart:ggml-cumsum-tri
32m 35s
model : add BailingMoeV2 support Server #20380: Pull request #16063 synchronize by CISC
31m 21s cisc/bailingmoe2
cisc/bailingmoe2
31m 21s
opencl: transposed gemm/gemv moe kernel with mxfp4,f32 Server #20379: Pull request #16602 synchronize by shawngu-quic
Action required CodeLinaro:moe-mxfp4-trans-reorder
CodeLinaro:moe-mxfp4-trans-reorder
Action required
support GLM-4.5V vision model Server #20378: Pull request #16600 synchronize by ddh0
Action required ddh0:glm45v-2
ddh0:glm45v-2
Action required
Morty Proxy This is a proxified and sanitized view of the page, visit original site.