Skip to content

Actions: ggml-org/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
11,833 workflow runs
11,833 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

json : support enum values within allOf Server #18611: Pull request #15830 synchronize by aldehir
September 6, 2025 22:43 18m 32s aldehir:fix-allOf-enum
aldehir:fix-allOf-enum
September 6, 2025 22:43 18m 32s
CUDA: faster tile FA (Pascal/AMD), headsize 256 (#15769) Server #18610: Commit 79bc429 pushed by JohannesGaessler
September 6, 2025 22:26 19m 6s master
master
September 6, 2025 22:26 19m 6s
ggml-zdnn: fix #15414, activate FP16 and BF16 acceleration and incorrect zTensor free Server #18609: Pull request #15839 synchronize by taronaeo
September 6, 2025 18:15 14m 31s taronaeo:fix/15414-llama-set-rows
taronaeo:fix/15414-llama-set-rows
September 6, 2025 18:15 14m 31s
ggml-zdnn: fix #15414, activate FP16 and BF16 acceleration and incorrect zTensor free Server #18608: Pull request #15839 synchronize by taronaeo
September 6, 2025 18:03 12m 23s taronaeo:fix/15414-llama-set-rows
taronaeo:fix/15414-llama-set-rows
September 6, 2025 18:03 12m 23s
ggml-zdnn: fix #15414, activate FP16 and BF16 acceleration and incorrect zTensor free Server #18607: Pull request #15839 opened by taronaeo
September 6, 2025 14:15 31m 49s taronaeo:fix/15414-llama-set-rows
taronaeo:fix/15414-llama-set-rows
September 6, 2025 14:15 31m 49s
kleidiai: generalize compute_forward_kv_cache to compute_forward_fp16… Server #18606: Commit c4df49a pushed by taronaeo
September 6, 2025 14:08 13m 54s master
master
September 6, 2025 14:08 13m 54s
llguidance : use attrs to determine special tokens Server #18605: Pull request #15837 synchronize by dstoc
September 6, 2025 13:45 26m 29s dstoc:llguidance-special-tokens
dstoc:llguidance-special-tokens
September 6, 2025 13:45 26m 29s
llguidance : use attrs to determine special tokens Server #18604: Pull request #15837 opened by dstoc
September 6, 2025 13:35 Action required dstoc:llguidance-special-tokens
dstoc:llguidance-special-tokens
September 6, 2025 13:35 Action required
server : speed up tests (#15836) Server #18603: Commit 3c3635d pushed by ngxson
September 6, 2025 12:45 29m 9s master
master
September 6, 2025 12:45 29m 9s
webgpu : fix build on emscripten Server #18602: Pull request #15826 synchronize by ngxson
September 6, 2025 12:26 36m 28s ngxson:xsn/emscripten_webgpu
ngxson:xsn/emscripten_webgpu
September 6, 2025 12:26 36m 28s
quantize: add option to automatically choose optimal quant types to reach a bpw target at lowest MSE error Server #18601: Pull request #15550 synchronize by EAddario
September 6, 2025 12:10 25m 50s EAddario:quantize
EAddario:quantize
September 6, 2025 12:10 25m 50s
imatrix: calculate activation-based statistics for new format (GGUF) imatrices Server #18600: Pull request #14891 synchronize by EAddario
September 6, 2025 12:09 13m 34s EAddario:imatrix
EAddario:imatrix
September 6, 2025 12:09 13m 34s
server : speed up tests Server #18599: Pull request #15836 synchronize by ngxson
September 6, 2025 11:51 20m 53s xsn/server_speedup_test
xsn/server_speedup_test
September 6, 2025 11:51 20m 53s
server : speed up tests Server #18598: Pull request #15836 synchronize by ngxson
September 6, 2025 11:38 13m 7s xsn/server_speedup_test
xsn/server_speedup_test
September 6, 2025 11:38 13m 7s
server : implement prompt processing progress report in stream mode (… Server #18597: Commit 61bdfd5 pushed by ngxson
September 6, 2025 11:35 33m 32s master
master
September 6, 2025 11:35 33m 32s
server : speed up tests Server #18596: Pull request #15836 synchronize by ngxson
September 6, 2025 11:34 4m 53s xsn/server_speedup_test
xsn/server_speedup_test
September 6, 2025 11:34 4m 53s
server : speed up tests Server #18595: Pull request #15836 opened by ngxson
September 6, 2025 11:30 4m 24s xsn/server_speedup_test
xsn/server_speedup_test
September 6, 2025 11:30 4m 24s
batched-bench : fix llama_synchronize usage during prompt processing Server #18594: Pull request #15835 opened by ggerganov
September 6, 2025 11:20 14m 26s gg/batched-bench-fix-synchronize
gg/batched-bench-fix-synchronize
September 6, 2025 11:20 14m 26s
ggml-cpu: document use of "free" memory [no ci] Server #18593: Pull request #15834 opened by JohannesGaessler
September 6, 2025 10:49 27m 58s JohannesGaessler:ggml-cpu-fix-free-memory
JohannesGaessler:ggml-cpu-fix-free-memory
September 6, 2025 10:49 27m 58s
server : implement prompt processing progress report in stream mode Server #18592: Pull request #15827 synchronize by ngxson
September 6, 2025 10:43 13m 37s xsn/server_progress_api
xsn/server_progress_api
September 6, 2025 10:43 13m 37s
server : implement prompt processing progress report in stream mode Server #18591: Pull request #15827 synchronize by ngxson
September 6, 2025 10:36 7m 12s xsn/server_progress_api
xsn/server_progress_api
September 6, 2025 10:36 7m 12s
server : implement prompt processing progress report in stream mode Server #18590: Pull request #15827 synchronize by ngxson
September 6, 2025 10:23 13m 30s xsn/server_progress_api
xsn/server_progress_api
September 6, 2025 10:23 13m 30s
vulkan: add mul_mat variant for embedded gpus Server #18589: Pull request #15800 synchronize by rmatif
September 6, 2025 09:59 12m 37s rmatif:vk-mulmat-embed
rmatif:vk-mulmat-embed
September 6, 2025 09:59 12m 37s
metal : make the backend async Server #18588: Pull request #15832 opened by ggerganov
September 6, 2025 09:28 14m 34s gg/metal-async
gg/metal-async
September 6, 2025 09:28 14m 34s
json : support enum values within allOf Server #18587: Pull request #15830 opened by aldehir
September 6, 2025 07:27 14m 0s aldehir:fix-allOf-enum
aldehir:fix-allOf-enum
September 6, 2025 07:27 14m 0s