Skip to content

Actions: ggml-org/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
11,484 workflow runs
11,484 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

model : add reasoning/tool parsing to Llama 3.x Nemotron Server #17261: Pull request #15083 synchronize by aldehir
August 7, 2025 00:54 Action required aldehir:model/llama-nemotron-reasoning
aldehir:model/llama-nemotron-reasoning
August 7, 2025 00:54 Action required
mtmd: server: Support basic multimodal data in /completions endpoint of server Server #17260: Pull request #15108 synchronize by 65a
August 7, 2025 00:31 12m 29s 65a:master
65a:master
August 7, 2025 00:31 12m 29s
mtmd: server: Support basic multimodal data in /completions endpoint of server Server #17259: Pull request #15108 synchronize by 65a
August 7, 2025 00:28 3m 57s 65a:master
65a:master
August 7, 2025 00:28 3m 57s
Add T5Gemma support #14940 Server #17258: Pull request #15123 synchronize by baonudesifeizhai
August 6, 2025 22:52 Action required baonudesifeizhai:t5gemma-support
baonudesifeizhai:t5gemma-support
August 6, 2025 22:52 Action required
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 Server #17257: Pull request #15131 synchronize by JohannesGaessler
August 6, 2025 22:46 11m 47s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
August 6, 2025 22:46 11m 47s
Add T5Gemma support #14940 Server #17256: Pull request #15123 synchronize by baonudesifeizhai
August 6, 2025 22:44 Action required baonudesifeizhai:t5gemma-support
baonudesifeizhai:t5gemma-support
August 6, 2025 22:44 Action required
ggml: Add basic SET_ROWS support in WebGPU (#15137) Server #17255: Commit 5fd160b pushed by reeselevine
August 6, 2025 22:14 13m 0s master
master
August 6, 2025 22:14 13m 0s
OpenCL: allow mixed f16/f32 add Server #17254: Pull request #15140 opened by rmatif
August 6, 2025 21:43 12m 1s rmatif:opencl-mixed-add
rmatif:opencl-mixed-add
August 6, 2025 21:43 12m 1s
fix profiling crash (#15072) Server #17253: Commit 756cfea pushed by max-krasnyansky
August 6, 2025 21:17 19m 9s master
master
August 6, 2025 21:17 19m 9s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 Server #17252: Pull request #15131 synchronize by JohannesGaessler
August 6, 2025 20:52 12m 18s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
August 6, 2025 20:52 12m 18s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 Server #17251: Pull request #15131 synchronize by JohannesGaessler
August 6, 2025 20:40 12m 37s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
August 6, 2025 20:40 12m 37s
gguf-py : add Numpy MXFP4 de/quantization support Server #17250: Pull request #15111 synchronize by compilade
August 6, 2025 20:33 16m 39s compilade/gguf-py-mxfp4
compilade/gguf-py-mxfp4
August 6, 2025 20:33 16m 39s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 Server #17249: Pull request #15131 synchronize by JohannesGaessler
August 6, 2025 20:21 12m 7s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
August 6, 2025 20:21 12m 7s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 Server #17248: Pull request #15131 synchronize by JohannesGaessler
August 6, 2025 20:14 6m 31s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
August 6, 2025 20:14 6m 31s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 Server #17247: Pull request #15131 synchronize by JohannesGaessler
August 6, 2025 20:06 8m 55s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
August 6, 2025 20:06 8m 55s
ggml: Add basic SET_ROWS support in WebGPU Server #17246: Pull request #15137 opened by reeselevine
August 6, 2025 19:32 29m 53s reeselevine:master
reeselevine:master
August 6, 2025 19:32 29m 53s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 Server #17245: Pull request #15131 synchronize by JohannesGaessler
August 6, 2025 19:20 30m 7s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
August 6, 2025 19:20 30m 7s
opencl: add swiglu_oai and add_id (#15121) Server #17244: Commit e725a1a pushed by max-krasnyansky
August 6, 2025 19:12 13m 40s master
master
August 6, 2025 19:12 13m 40s
chat : support Granite model reasoning and tool call (#14864) Server #17243: Commit 3db4da5 pushed by CISC
August 6, 2025 18:27 17m 58s master
master
August 6, 2025 18:27 17m 58s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 Server #17242: Pull request #15131 synchronize by JohannesGaessler
August 6, 2025 18:14 13m 21s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
August 6, 2025 18:14 13m 21s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 Server #17241: Pull request #15131 opened by JohannesGaessler
August 6, 2025 17:38 12m 51s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
August 6, 2025 17:38 12m 51s
Fixed name -override-tensors to -override-tensor (#15129) Server #17240: Commit 476aa3f pushed by jukofyork
August 6, 2025 16:28 45m 38s master
master
August 6, 2025 16:28 45m 38s
llama-bench: fixed help output for -override-tensors to -override-tensor Server #17239: Pull request #15129 opened by jukofyork
August 6, 2025 16:24 12m 19s jukofyork:llama-bench-fix
jukofyork:llama-bench-fix
August 6, 2025 16:24 12m 19s
Adding chat template support for Granite model Server #17238: Pull request #14864 synchronize by smdesai
August 6, 2025 16:23 14m 55s smdesai:master
smdesai:master
August 6, 2025 16:23 14m 55s
Adding chat template support for Granite model Server #17237: Pull request #14864 synchronize by smdesai
August 6, 2025 15:51 5m 56s smdesai:master
smdesai:master
August 6, 2025 15:51 5m 56s