Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
11,336 workflow runs
11,336 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[CUDA] Enable CUDA Graph on CUDA Toolkit < 12.x CI #20323: Pull request #12394 opened by gaugarg-nv
March 14, 2025 15:45 Action required gaugarg-nv:enable_cuda_graph_on_11.x
gaugarg-nv:enable_cuda_graph_on_11.x
March 14, 2025 15:45 Action required
SYCL: Delete redundant plus sign and space CI #20322: Pull request #12391 opened by aubreyli
March 14, 2025 14:41 48m 37s aubreyli:master
aubreyli:master
March 14, 2025 14:41 48m 37s
SYCL: set extras only on GGML_TYPE_Q4_0 CI #20321: Pull request #12366 synchronize by qnixsynapse
March 14, 2025 14:39 49m 9s qnixsynapse:fix/memory_leak
qnixsynapse:fix/memory_leak
March 14, 2025 14:39 49m 9s
server: streaming of tool calls and thoughts when --jinja is on CI #20320: Pull request #12379 synchronize by ochafik
March 14, 2025 13:05 1h 9m 17s ochafik:tool-diffs
ochafik:tool-diffs
March 14, 2025 13:05 1h 9m 17s
server: streaming of tool calls and thoughts when --jinja is on CI #20319: Pull request #12379 synchronize by ochafik
March 14, 2025 13:01 4m 31s ochafik:tool-diffs
ochafik:tool-diffs
March 14, 2025 13:01 4m 31s
Load all MoE experts during warmup (#11571) CI #20318: Commit 8fcb563 pushed by fairydreaming
March 14, 2025 12:47 1h 3m 31s master
master
March 14, 2025 12:47 1h 3m 31s
SYCL: Remove misleading ggml_sycl_op_flatten function CI #20317: Pull request #12387 synchronize by qnixsynapse
March 14, 2025 12:11 1h 7m 50s qnixsynapse:remove_op_flatten_fn
qnixsynapse:remove_op_flatten_fn
March 14, 2025 12:11 1h 7m 50s
SYCL: Remove misleading ggml_sycl_op_flatten function CI #20316: Pull request #12387 synchronize by qnixsynapse
March 14, 2025 12:10 1m 54s qnixsynapse:remove_op_flatten_fn
qnixsynapse:remove_op_flatten_fn
March 14, 2025 12:10 1m 54s
server: streaming of tool calls and thoughts when --jinja is on CI #20315: Pull request #12379 synchronize by ochafik
March 14, 2025 12:07 54m 51s ochafik:tool-diffs
ochafik:tool-diffs
March 14, 2025 12:07 54m 51s
SYCL: Remove misleading ggml_sycl_op_flatten function CI #20314: Pull request #12387 opened by qnixsynapse
March 14, 2025 12:06 3m 44s qnixsynapse:remove_op_flatten_fn
qnixsynapse:remove_op_flatten_fn
March 14, 2025 12:06 3m 44s
server: streaming of tool calls and thoughts when --jinja is on CI #20313: Pull request #12379 synchronize by ochafik
March 14, 2025 12:02 5m 3s ochafik:tool-diffs
ochafik:tool-diffs
March 14, 2025 12:02 5m 3s
SYCL: using graphs is configurable by environment variable and compile option CI #20312: Pull request #12371 synchronize by lslusarczyk
March 14, 2025 11:42 1h 4m 4s lslusarczyk:sycl-graphs
lslusarczyk:sycl-graphs
March 14, 2025 11:42 1h 4m 4s
SYCL: using graphs is configurable by environment variable and compile option CI #20311: Pull request #12371 synchronize by lslusarczyk
March 14, 2025 11:38 2m 55s lslusarczyk:sycl-graphs
lslusarczyk:sycl-graphs
March 14, 2025 11:38 2m 55s
SYCL: using graphs is configurable by environment variable and compile option CI #20310: Pull request #12371 synchronize by lslusarczyk
March 14, 2025 11:04 Action required lslusarczyk:sycl-graphs
lslusarczyk:sycl-graphs
March 14, 2025 11:04 Action required
llama : add llama_batch_ext CI #20309: Pull request #11875 synchronize by ngxson
March 14, 2025 10:28 1h 50m 39s ngxson:xsn/private_batch_api
ngxson:xsn/private_batch_api
March 14, 2025 10:28 1h 50m 39s
llama : add llama_batch_ext CI #20308: Pull request #11875 synchronize by ngxson
March 14, 2025 10:25 3m 2s ngxson:xsn/private_batch_api
ngxson:xsn/private_batch_api
March 14, 2025 10:25 3m 2s
server: fix "--grammar-file" parameter (#12285) CI #20307: Commit add2a3a pushed by ngxson
March 14, 2025 10:21 1h 39m 5s master
master
March 14, 2025 10:21 1h 39m 5s
llama : add llama_batch_ext CI #20306: Pull request #11875 synchronize by ngxson
March 14, 2025 09:47 38m 40s ngxson:xsn/private_batch_api
ngxson:xsn/private_batch_api
March 14, 2025 09:47 38m 40s
[WIP] MUSA: enable fastfp16, correct warp reduce impl and perf tuning CI #20305: Pull request #12383 opened by BodhiHu
March 14, 2025 09:36 1h 19m 54s BodhiHu:musa
BodhiHu:musa
March 14, 2025 09:36 1h 19m 54s
Load all MoE experts during warmup CI #20304: Pull request #11571 synchronize by fairydreaming
March 14, 2025 09:30 1h 55m 17s fairydreaming:experts-warmup
fairydreaming:experts-warmup
March 14, 2025 09:30 1h 55m 17s
Load all MoE experts during warmup CI #20303: Pull request #11571 reopened by fairydreaming
March 14, 2025 09:19 12m 0s fairydreaming:experts-warmup
fairydreaming:experts-warmup
March 14, 2025 09:19 12m 0s
Load all MoE experts during warmup CI #20302: Pull request #11571 synchronize by fairydreaming
March 14, 2025 09:19 59m 15s fairydreaming:experts-warmup
fairydreaming:experts-warmup
March 14, 2025 09:19 59m 15s
ggml : fix quantized cpy op CI #20301: Pull request #12310 synchronize by ggerganov
March 14, 2025 09:00 51m 31s gg/cpu-fix-cpy-q
gg/cpu-fix-cpy-q
March 14, 2025 09:00 51m 31s
graph : simplify attn input build for unified KV cache (#12381) CI #20300: Commit c522ce4 pushed by ggerganov
March 14, 2025 08:47 45m 26s master
master
March 14, 2025 08:47 45m 26s
[CANN]MUL_MAT optimization CI #20299: Pull request #12382 synchronize by noemotiovon
March 14, 2025 08:10 45m 58s noemotiovon:mat_mul
noemotiovon:mat_mul
March 14, 2025 08:10 45m 58s