Skip to content

Actions: vllm-project/vllm-ascend

Actions

ascend test / nightly-a2

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
vllm_ascend_test_nightly_a2.yaml
3,365 workflow runs
3,365 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Feat] Add custom Embedding tensor model parallel ascend test / nightly-a2 #3384: Pull request #2616 synchronize by zzhx1
1s lidenghui1110:embedding_tp
lidenghui1110:embedding_tp
1s
[Feat] Add custom Embedding tensor model parallel ascend test / nightly-a2 #3383: Pull request #2616 synchronize by zzhx1
Skipped lidenghui1110:embedding_tp
lidenghui1110:embedding_tp
Skipped
[bugfix] Repair the problem of moe model accuracy caused by version upgrade. ascend test / nightly-a2 #3382: Pull request #4562 synchronize by weijinqian0
1s weijinqian0:bugfix_moe_main
weijinqian0:bugfix_moe_main
1s
ascend test / nightly-a2 ascend test / nightly-a2 #3381: Scheduled
1h 24m 16s main
main
1h 24m 16s
[EPLB][Ops] Integerate grouped_matmul_swiglu_quant_weight_nz_tensor_list operator into dynamic EPLB ascend test / nightly-a2 #3380: Pull request #4216 synchronize by 845473182
1s 845473182:gmm_swiglu_quant_tensor_list
845473182:gmm_swiglu_quant_tensor_list
1s
[Bugfix] Fix kvpool precision synchronization ascend test / nightly-a2 #3379: Pull request #4574 synchronize by LCAIZJ
1s LCAIZJ:dev
LCAIZJ:dev
1s
[Bugfix] Fix kvpool precision synchronization ascend test / nightly-a2 #3378: Pull request #4574 synchronize by LCAIZJ
1s LCAIZJ:dev
LCAIZJ:dev
1s
[MM][Model] Remove Qwen3-VL modeling files ascend test / nightly-a2 #3377: Pull request #4577 synchronize by shen-shanshan
1s shen-shanshan:rm-3vl
shen-shanshan:rm-3vl
1s
[feature] Support W8A8 PD-Mix Quantization ascend test / nightly-a2 #3376: Pull request #4235 synchronize by SlightwindSec
2s SlightwindSec:w8a8_pdmix
SlightwindSec:w8a8_pdmix
2s
[MM][Model] Remove Qwen3-VL modeling files ascend test / nightly-a2 #3375: Pull request #4577 synchronize by shen-shanshan
1s shen-shanshan:rm-3vl
shen-shanshan:rm-3vl
1s
[CI] Skip test_ngram_correctness as the oom issue block CI ascend test / nightly-a2 #3374: Pull request #4578 synchronize by MengqingCao
1s MengqingCao:ngram
MengqingCao:ngram
1s
[OPS] add bmm_transpose ops ascend test / nightly-a2 #3373: Pull request #3990 synchronize by hust17yixuan
2s hust17yixuan:bmm_transpose
hust17yixuan:bmm_transpose
2s
[OPS] add bmm_transpose ops ascend test / nightly-a2 #3372: Pull request #3990 synchronize by hust17yixuan
1s hust17yixuan:bmm_transpose
hust17yixuan:bmm_transpose
1s
[MM][Model] Remove Qwen3-VL modeling files ascend test / nightly-a2 #3371: Pull request #4577 labeled by shen-shanshan
2s shen-shanshan:rm-3vl
shen-shanshan:rm-3vl
2s
[MM][Model] Remove Qwen3-VL modeling files ascend test / nightly-a2 #3370: Pull request #4577 labeled by shen-shanshan
1s shen-shanshan:rm-3vl
shen-shanshan:rm-3vl
1s
[MM][Model] Remove Qwen3-VL modeling files ascend test / nightly-a2 #3369: Pull request #4577 synchronize by shen-shanshan
1s shen-shanshan:rm-3vl
shen-shanshan:rm-3vl
1s
[EPLB][Ops] Integerate grouped_matmul_swiglu_quant_weight_nz_tensor_list operator into dynamic EPLB ascend test / nightly-a2 #3368: Pull request #4216 labeled by weijinqian0
Skipped 845473182:gmm_swiglu_quant_tensor_list
845473182:gmm_swiglu_quant_tensor_list
Skipped
[EPLB][Ops] Integerate grouped_matmul_swiglu_quant_weight_nz_tensor_list operator into dynamic EPLB ascend test / nightly-a2 #3367: Pull request #4216 labeled by weijinqian0
1s 845473182:gmm_swiglu_quant_tensor_list
845473182:gmm_swiglu_quant_tensor_list
1s
[CI] Skip test_ngram_correctness as the oom issue block CI ascend test / nightly-a2 #3366: Pull request #4578 labeled by MengqingCao
1s MengqingCao:ngram
MengqingCao:ngram
1s
[CI] Skip test_ngram_correctness as the oom issue block CI ascend test / nightly-a2 #3365: Pull request #4578 labeled by MengqingCao
1s MengqingCao:ngram
MengqingCao:ngram
1s
[OPS] add bmm_transpose ops ascend test / nightly-a2 #3364: Pull request #3990 synchronize by hust17yixuan
1s hust17yixuan:bmm_transpose
hust17yixuan:bmm_transpose
1s
[Feat] shared expert dp for deepseek_mtp ascend test / nightly-a2 #3363: Pull request #3811 synchronize by zengzengran
Action required dragondream-chen:main
dragondream-chen:main
Action required
[feature] Support W8A8 PD-Mix Quantization ascend test / nightly-a2 #3362: Pull request #4235 synchronize by SlightwindSec
1s SlightwindSec:w8a8_pdmix
SlightwindSec:w8a8_pdmix
1s
[EPLB][Ops] Integerate grouped_matmul_swiglu_quant_weight_nz_tensor_list operator into dynamic EPLB ascend test / nightly-a2 #3361: Pull request #4216 synchronize by 845473182
1s 845473182:gmm_swiglu_quant_tensor_list
845473182:gmm_swiglu_quant_tensor_list
1s
[feature] Support W8A8 PD-Mix Quantization ascend test / nightly-a2 #3360: Pull request #4235 synchronize by SlightwindSec
1s SlightwindSec:w8a8_pdmix
SlightwindSec:w8a8_pdmix
1s