Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
6,411 workflow run results
6,411 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

vulkan: enable fp16 for gcn 3 and 4 chips CI #22317: Pull request #13396 opened by netrunnereve
47m 27s fp16
fp16
47m 27s
llama : do not crash if there is no CPU backend CI #22316: Pull request #13395 synchronize by slaren
44m 44s sl/fix-missing-cpu-backend-crash
sl/fix-missing-cpu-backend-crash
44m 44s
llama : do not crash if there is no CPU backend CI #22315: Pull request #13395 opened by slaren
14m 16s sl/fix-missing-cpu-backend-crash
sl/fix-missing-cpu-backend-crash
14m 16s
llama/ggml: add LLM training support CI #22314: Pull request #10544 synchronize by JohannesGaessler
59m 0s JohannesGaessler:llama-opt-3
JohannesGaessler:llama-opt-3
59m 0s
ci : limit write permission to only the release step + fixes (#13392) CI #22313: Commit 15e0328 pushed by slaren
50m 59s master
master
50m 59s
ci : limit write permission to only the release step + fixes CI #22312: Pull request #13392 opened by slaren
53m 45s sl/workflow-permissions
sl/workflow-permissions
53m 45s
grammar: handle misplaced special regex chars [*+?] CI #22311: Pull request #13391 opened by rick-github
42m 31s rick-github:grammar
rick-github:grammar
42m 31s
Add --parse-special for enabling parsing of special tokens in imatrix calculation CI #22310: Pull request #13389 synchronize by bartowski1182
46m 54s bartowski1182:special_imatrix
bartowski1182:special_imatrix
46m 54s
vulkan: scalar flash attention implementation CI #22309: Pull request #13324 synchronize by jeffbolznv
51m 49s jeffbolznv:scalar_fa_3
jeffbolznv:scalar_fa_3
51m 49s
Add --parse-special for enabling parsing of special tokens in imatrix calculation CI #22308: Pull request #13389 opened by bartowski1182
44m 12s bartowski1182:special_imatrix
bartowski1182:special_imatrix
44m 12s
metal : optimize MoE for large batches CI #22307: Pull request #13388 opened by ggerganov
44m 52s gg/metal-mm-id-opt
gg/metal-mm-id-opt
44m 52s
mtmd : Expose helper_decode_image_chunk (#13366) CI #22306: Commit f05a6d7 pushed by ngxson
51m 35s master
master
51m 35s
Update llama-quant.cpp llama_tensor_get_type with DeepSeek friendly modifications CI #22305: Pull request #12727 synchronize by bartowski1182
1h 1m 48s bartowski1182:quant_types
bartowski1182:quant_types
1h 1m 48s
mtmd: Expose helper_decode_image_chunk CI #22304: Pull request #13366 synchronize by mattjcly
1h 24m 8s mattjcly:mtmd-api-extension
mattjcly:mtmd-api-extension
1h 24m 8s
mtmd: Expose helper_decode_image_chunk CI #22303: Pull request #13366 synchronize by mattjcly
32m 39s mattjcly:mtmd-api-extension
mattjcly:mtmd-api-extension
32m 39s
Add --no-op-offload to improve -ot pp perf in MoE models like llama4 400B CI #22302: Pull request #13386 opened by hjc4869
2h 47m 28s hjc4869:no_op_offload
hjc4869:no_op_offload
2h 47m 28s
arg : add model catalog CI #22301: Pull request #13385 opened by ngxson
1h 58m 1s ngxson:xsn/arg_add_catalog
ngxson:xsn/arg_add_catalog
1h 58m 1s
kv-cache : add SWA support CI #22300: Pull request #13194 synchronize by ggerganov
2h 33m 41s gg/swa
gg/swa
2h 33m 41s
ggml-cpu: Integrate fp32=bf16xbf16 SME KleidiAI kernel CI #22299: Pull request #13053 synchronize by eddnjjn
2h 18m 40s eddnjjn:feature/fp32_sme_kernel
eddnjjn:feature/fp32_sme_kernel
2h 18m 40s
CUDA: fix crash on large batch size for MoE models CI #22298: Pull request #13384 opened by JohannesGaessler
1h 51m 50s JohannesGaessler:cuda-fix-moe-max-ub
JohannesGaessler:cuda-fix-moe-max-ub
1h 51m 50s
vulkan: scalar flash attention implementation CI #22297: Pull request #13324 synchronize by jeffbolznv
1h 27m 40s jeffbolznv:scalar_fa_3
jeffbolznv:scalar_fa_3
1h 27m 40s
server : vision support via libmtmd CI #22296: Pull request #12898 synchronize by ngxson
1h 39m 19s ngxson:xsn/server_mtmd
ngxson:xsn/server_mtmd
1h 39m 19s
server : (webui) revamp the input area, plus many small UI improvemen… CI #22295: Commit 8c83449 pushed by ngxson
3h 37m 9s master
master
3h 37m 9s
server : (webui) revamp the input area, plus many small UI improvements CI #22294: Pull request #13365 synchronize by ngxson
1h 31m 12s ngxson:xsn/webui_rework_input
ngxson:xsn/webui_rework_input
1h 31m 12s
server : (webui) revamp the input area, plus many small UI improvements CI #22293: Pull request #13365 synchronize by ngxson
11m 35s ngxson:xsn/webui_rework_input
ngxson:xsn/webui_rework_input
11m 35s
ProTip! You can narrow down the results and go further in time using created:<2025-05-08 or the other filters available.