Skip to content

Actions: intel/auto-round

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
6,562 workflow runs
6,562 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

support hadamard transform for mxfp4 with rtn or autoround method. CodeQL Advanced #1269: Pull request #1349 synchronize by pre-commit-ci bot
Action required lkk12014402:mxfp4_hadamard_transform
lkk12014402:mxfp4_hadamard_transform
Action required
support hadamard transform for mxfp4 with rtn or autoround method. Compatibility Test on ARM64 #1351: Pull request #1349 synchronize by pre-commit-ci bot
Action required lkk12014402:mxfp4_hadamard_transform
lkk12014402:mxfp4_hadamard_transform
Action required
support hadamard transform for mxfp4 with rtn or autoround method. Compatibility Test on ARM64 #1350: Pull request #1349 synchronize by lkk12014402
21m 25s lkk12014402:mxfp4_hadamard_transform
lkk12014402:mxfp4_hadamard_transform
21m 25s
support hadamard transform for mxfp4 with rtn or autoround method. CodeQL Advanced #1268: Pull request #1349 synchronize by lkk12014402
1m 27s lkk12014402:mxfp4_hadamard_transform
lkk12014402:mxfp4_hadamard_transform
1m 27s
Fix #1284: preserve FP8 format for layers specified in ignore_layers CodeQL Advanced #1267: Pull request #1511 opened by LuciferDono
Action required LuciferDono:LuciferDono/fp8-ignore-layers
LuciferDono:LuciferDono/fp8-ignore-layers
Action required
Fix #1284: preserve FP8 format for layers specified in ignore_layers Compatibility Test on ARM64 #1349: Pull request #1511 opened by LuciferDono
Action required LuciferDono:LuciferDono/fp8-ignore-layers
LuciferDono:LuciferDono/fp8-ignore-layers
Action required
Nightly Binary Build and Publish Nightly Binary Build and Publish #59: Scheduled
16s main
main
16s
Nightly Binary Build and Publish Nightly Binary Build and Publish #58: Scheduled
19s main
main
19s
Copilot code review Copilot code review #32: by Copilot AI
2m 33s refs/pull/1508/head
refs/pull/1508/head
2m 33s
support minimax_m2 ignore layer: block_sparse_moe.gate CodeQL Advanced #1266: Pull request #1508 opened by xin3he
1m 15s xin3he-patch-1
xin3he-patch-1
1m 15s
support minimax_m2 ignore layer: block_sparse_moe.gate Compatibility Test on ARM64 #1348: Pull request #1508 opened by xin3he
26m 51s xin3he-patch-1
xin3he-patch-1
26m 51s
release CUDA memory in WeightConverter and avoid meaningless print Compatibility Test on ARM64 #1347: Pull request #1498 synchronize by xin3he
25m 54s xinhe/3-5
xinhe/3-5
25m 54s
release CUDA memory in WeightConverter and avoid meaningless print CodeQL Advanced #1265: Pull request #1498 synchronize by xin3he
1m 11s xinhe/3-5
xinhe/3-5
1m 11s
CodeQL Advanced CodeQL Advanced #1264: Scheduled
13m 7s main
main
13m 7s
Enable CUDA CI CodeQL Advanced #1263: Pull request #1473 synchronize by XuehaoSun
15m 6s xuehao/cuda-ci
xuehao/cuda-ci
15m 6s
reduce ram&vram usage for vlm calib stage CodeQL Advanced #1262: Pull request #1488 synchronize by WeiweiZhang1
36m 36s reduce_vram/ram_usage_for_vlm_in_calib_stage
reduce_vram/ram_usage_for_vlm_in_calib_stage
36m 36s
reduce ram&vram usage for vlm calib stage Compatibility Test on ARM64 #1346: Pull request #1488 synchronize by WeiweiZhang1
35m 43s reduce_vram/ram_usage_for_vlm_in_calib_stage
reduce_vram/ram_usage_for_vlm_in_calib_stage
35m 43s
reduce ram&vram usage for vlm calib stage CodeQL Advanced #1261: Pull request #1488 synchronize by pre-commit-ci bot
34m 36s reduce_vram/ram_usage_for_vlm_in_calib_stage
reduce_vram/ram_usage_for_vlm_in_calib_stage
34m 36s
reduce ram&vram usage for vlm calib stage Compatibility Test on ARM64 #1345: Pull request #1488 synchronize by pre-commit-ci bot
20s reduce_vram/ram_usage_for_vlm_in_calib_stage
reduce_vram/ram_usage_for_vlm_in_calib_stage
20s
reduce ram&vram usage for vlm calib stage CodeQL Advanced #1260: Pull request #1488 synchronize by WeiweiZhang1
22m 1s reduce_vram/ram_usage_for_vlm_in_calib_stage
reduce_vram/ram_usage_for_vlm_in_calib_stage
22m 1s
reduce ram&vram usage for vlm calib stage Compatibility Test on ARM64 #1344: Pull request #1488 synchronize by WeiweiZhang1
40s reduce_vram/ram_usage_for_vlm_in_calib_stage
reduce_vram/ram_usage_for_vlm_in_calib_stage
40s
Enable CUDA CI CodeQL Advanced #1259: Pull request #1473 synchronize by XuehaoSun
24m 3s xuehao/cuda-ci
xuehao/cuda-ci
24m 3s
Fix FP8 quantizer for Transformers v4 CodeQL Advanced #1258: Pull request #1504 synchronize by yiliu30
1m 7s hpu-v4
hpu-v4
1m 7s
Fix FP8 quantizer for Transformers v4 Compatibility Test on ARM64 #1343: Pull request #1504 synchronize by yiliu30
24m 21s hpu-v4
hpu-v4
24m 21s
Enable CUDA CI CodeQL Advanced #1257: Pull request #1473 synchronize by XuehaoSun
1m 8s xuehao/cuda-ci
xuehao/cuda-ci
1m 8s