Skip to content

Actions: mudler/vllm.cpp

Actions

ci

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
ci.yml
2,500+ workflow runs
2,500+ workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
measure(MODEL-NEMOTRON-H-ABI-A2P): the first Nemotron speed numbers, and the KV budget that makes them comparable (#1250) ci #3783: Pull request #1251 synchronize by localai-bot
Pending row/MODEL-NEMOTRON-H-ABI-A2P-speed
row/MODEL-NEMOTRON-H-ABI-A2P-speed
Pending
fix(LTX25-TEXT-LINEAR-SEAM): the caption projection is one core for 671 s per pass, so route it through vt::MatmulBT ci #3782: Pull request #1252 closed by localai-bot
Pending row/LTX25-TEXT-LINEAR-SEAM
row/LTX25-TEXT-LINEAR-SEAM
Pending
fix(LTX25-TEXT-LINEAR-SEAM): the caption projection is one core for 6… ci #3781: Commit 7b9e207 pushed by localai-bot
Pending main
main
Pending
record(MODEL-TEXT-nemotron-h): the row is blocked on a kernel that landed, and a file glob is why nobody saw it ci #3780: Pull request #1081 synchronize by localai-bot
Queued row/RECORDS-NEMOTRON-H-MATRIX-1074
row/RECORDS-NEMOTRON-H-MATRIX-1074
Queued
fix(LTX25-TEXT-LINEAR-SEAM): the caption projection is one core for 671 s per pass, so route it through vt::MatmulBT ci #3779: Pull request #1252 synchronize by localai-bot
Queued row/LTX25-TEXT-LINEAR-SEAM
row/LTX25-TEXT-LINEAR-SEAM
Queued
measure(MODEL-NEMOTRON-H-ABI-A2P): the first Nemotron speed numbers, and the KV budget that makes them comparable (#1250) ci #3778: Pull request #1251 synchronize by localai-bot
Queued row/MODEL-NEMOTRON-H-ABI-A2P-speed
row/MODEL-NEMOTRON-H-ABI-A2P-speed
Queued
fix(LTX25-TEXT-LINEAR-SEAM): the caption projection is one core for 671 s per pass, so route it through vt::MatmulBT ci #3777: Pull request #1252 synchronize by localai-bot
10m 13s row/LTX25-TEXT-LINEAR-SEAM
row/LTX25-TEXT-LINEAR-SEAM
10m 13s
fix(#1157): NemotronH decoded with STALE input ids, and the recurrent carry was never the cause ci #3776: Pull request #1221 closed by localai-bot
39m 50s row/MODEL-NEMOTRON-H-ABI-A2P-1157-fix
row/MODEL-NEMOTRON-H-ABI-A2P-1157-fix
39m 50s
fix(LTX25-TEXT-LINEAR-SEAM): the caption projection is one core for 671 s per pass, so route it through vt::MatmulBT ci #3775: Pull request #1252 opened by localai-bot
45m 57s row/LTX25-TEXT-LINEAR-SEAM
row/LTX25-TEXT-LINEAR-SEAM
45m 57s
measure(MODEL-NEMOTRON-H-ABI-A2P): the first Nemotron speed numbers, and the KV budget that makes them comparable (#1250) ci #3774: Pull request #1251 opened by localai-bot
49m 24s row/MODEL-NEMOTRON-H-ABI-A2P-speed
row/MODEL-NEMOTRON-H-ABI-A2P-speed
49m 24s
record(LTX25-DECODE-SPEED): three scalar single-threaded loops in the LTX CPU path, and the number ltx2_video.cpp said was owed ci #3773: Pull request #1214 closed by localai-bot
7m 31s record/ltx25-scalar-cpu-path
record/ltx25-scalar-cpu-path
7m 31s
record(LTX25-DECODE-SPEED): three scalar single-threaded loops in the… ci #3772: Commit 839d243 pushed by localai-bot
1h 11m 26s main
main
1h 11m 26s
record(LTX25-DECODE-SPEED): three scalar single-threaded loops in the LTX CPU path, and the number ltx2_video.cpp said was owed ci #3771: Pull request #1214 synchronize by localai-bot
29s record/ltx25-scalar-cpu-path
record/ltx25-scalar-cpu-path
29s
feat(LTX25-KEYFRAME-INTERP): the interpolation pipeline, on the conditioning builder that has no frame-0 branch (#1096) ci #3770: Pull request #1209 closed by localai-bot
9m 50s row/LTX25-KEYFRAME-INTERP
row/LTX25-KEYFRAME-INTERP
9m 50s
feat(LTX25-KEYFRAME-INTERP): the interpolation pipeline, on the condi… ci #3769: Commit 6f0e6b7 pushed by localai-bot
2m 15s main
main
2m 15s
ci ci #3768: Scheduled
Queued main
main
Queued
record(MODEL-TEXT-nemotron-h): the row is blocked on a kernel that landed, and a file glob is why nobody saw it ci #3767: Pull request #1081 synchronize by localai-bot
1h 23m 34s row/RECORDS-NEMOTRON-H-MATRIX-1074
row/RECORDS-NEMOTRON-H-MATRIX-1074
1h 23m 34s
fix(#1157): NemotronH decoded with STALE input ids, and the recurrent carry was never the cause ci #3766: Pull request #1221 synchronize by localai-bot
1h 33m 36s row/MODEL-NEMOTRON-H-ABI-A2P-1157-fix
row/MODEL-NEMOTRON-H-ABI-A2P-1157-fix
1h 33m 36s
record(MODEL-TEXT-nemotron-h): the row is blocked on a kernel that landed, and a file glob is why nobody saw it ci #3765: Pull request #1081 synchronize by localai-bot
18m 44s row/RECORDS-NEMOTRON-H-MATRIX-1074
row/RECORDS-NEMOTRON-H-MATRIX-1074
18m 44s
fix(rocm): #785 runtime arch dispatch — launch SharedKWmma prefill where it exists ci #3764: Pull request #1186 closed by localai-bot
50m 46s bakon11:fix/785-wmma-runtime-dispatch
bakon11:fix/785-wmma-runtime-dispatch
50m 46s
fix(rocm): #785 runtime arch dispatch, launch SharedKWmma prefill whe… ci #3763: Commit ae581da pushed by localai-bot
41m 2s main
main
41m 2s
record(MODEL-TEXT-nemotron-h): the row is blocked on a kernel that landed, and a file glob is why nobody saw it ci #3762: Pull request #1081 synchronize by localai-bot
52m 32s row/RECORDS-NEMOTRON-H-MATRIX-1074
row/RECORDS-NEMOTRON-H-MATRIX-1074
52m 32s
fix(ENG-RECORD-CONFLICT-SURFACES): retire MAX_README_CHARS, the fourt… ci #3761: Commit dabf337 pushed by localai-bot
3m 7s main
main
3m 7s
fix(ENG-RECORD-CONFLICT-SURFACES): retire MAX_README_CHARS, the fourth whole-file budget (#498) ci #3760: Pull request #1245 closed by localai-bot
53m 54s row/ENG-RECORD-CONFLICT-SURFACES-498
row/ENG-RECORD-CONFLICT-SURFACES-498
53m 54s
feat(SPEC-DSPARK-QWEN3-ROUTING): give a Qwen3 DSpark draft an explicit route, and refuse the DeepSeek-V4 lane by name ci #3759: Pull request #1248 closed by localai-bot
56m 1s row/DSPARK-QWEN3-ROUTING-IMPL
row/DSPARK-QWEN3-ROUTING-IMPL
56m 1s