Skip to content

Actions: HabanaAI/vllm-fork

Actions

cpu-test

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
cpu-test.yml
1,120 workflow runs
1,120 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[SW-197036] - use torch._scaled_mm with hpu cpu-test #1193: Pull request #660 synchronize by nirda7
January 8, 2025 16:19 3m 4s remove_scaled_mm_wa
remove_scaled_mm_wa
January 8, 2025 16:19 3m 4s
Add mark_step for encoder layers (#669) cpu-test #1192: Commit 49a11e2 pushed by michalkuligowski
January 8, 2025 15:58 3m 3s habana_main
habana_main
January 8, 2025 15:58 3m 3s
Add mllama support to benchmark_throughput (#668) cpu-test #1191: Commit 8f53dee pushed by kdamaszk
January 8, 2025 11:55 3m 13s habana_main
habana_main
January 8, 2025 11:55 3m 13s
Add mllama support to benchmark_throughput cpu-test #1190: Pull request #668 synchronize by kdamaszk
January 8, 2025 11:51 3m 19s dev/kdamaszke/add-mllama-to-benchmark-throughput
dev/kdamaszke/add-mllama-to-benchmark-throughput
January 8, 2025 11:51 3m 19s
Add llava support to benchmark_throuhput (#665) cpu-test #1189: Commit 585ca9a pushed by michalkuligowski
January 8, 2025 11:37 3m 1s habana_main
habana_main
January 8, 2025 11:37 3m 1s
Add mark_step for encoder layers cpu-test #1188: Pull request #669 synchronize by yma11
January 8, 2025 08:01 3m 17s yma11:mark_step
yma11:mark_step
January 8, 2025 08:01 3m 17s
Add mark_step for encoder layers cpu-test #1187: Pull request #669 opened by yma11
January 8, 2025 03:27 3m 15s yma11:mark_step
yma11:mark_step
January 8, 2025 03:27 3m 15s
Add inc fp8 qunatization documentation cpu-test #1186: Pull request #635 synchronize by nirda7
January 7, 2025 15:22 3m 4s fp8_quantization_documentation
fp8_quantization_documentation
January 7, 2025 15:22 3m 4s
Add inc fp8 qunatization documentation cpu-test #1185: Pull request #635 synchronize by nirda7
January 7, 2025 14:46 3m 0s fp8_quantization_documentation
fp8_quantization_documentation
January 7, 2025 14:46 3m 0s
Add llava support to benchmark_throuhput cpu-test #1184: Pull request #665 synchronize by adobrzyniewicz-habana
January 7, 2025 14:18 3m 12s adobrzyniewicz/benchamrk_throughput_add_llava_support
adobrzyniewicz/benchamrk_throughput_add_llava_support
January 7, 2025 14:18 3m 12s
[SW-197036] - use torch._scaled_mm with hpu cpu-test #1183: Pull request #660 synchronize by nirda7
January 7, 2025 12:51 3m 0s remove_scaled_mm_wa
remove_scaled_mm_wa
January 7, 2025 12:51 3m 0s
Add inc fp8 qunatization documentation cpu-test #1182: Pull request #635 synchronize by nirda7
January 7, 2025 12:11 3m 10s fp8_quantization_documentation
fp8_quantization_documentation
January 7, 2025 12:11 3m 10s
[bugfix] fix RuntimeError on apc (#648) cpu-test #1181: Commit 5d582b5 pushed by michalkuligowski
January 7, 2025 11:02 3m 8s habana_main
habana_main
January 7, 2025 11:02 3m 8s
Use FusedSDPA for MllamaVisionSdpaAttention cpu-test #1180: Pull request #620 synchronize by kdamaszk
January 7, 2025 10:25 2m 57s dev/kdamaszke/mllama_fusedsdpa
dev/kdamaszke/mllama_fusedsdpa
January 7, 2025 10:25 2m 57s
Add mllama support to benchmark_throughput cpu-test #1179: Pull request #668 opened by kdamaszk
January 7, 2025 10:24 3m 2s dev/kdamaszke/add-mllama-to-benchmark-throughput
dev/kdamaszke/add-mllama-to-benchmark-throughput
January 7, 2025 10:24 3m 2s
Limit number of dummy cross attention blocks cpu-test #1178: Pull request #667 opened by kdamaszk
January 7, 2025 10:21 3m 9s dev/kdamaszke/fix-encoder-warmup
dev/kdamaszke/fix-encoder-warmup
January 7, 2025 10:21 3m 9s
Optimize for topk=1 case if we do not handle duplicates (#603) cpu-test #1177: Commit 9d6917f pushed by michalkuligowski
January 7, 2025 09:37 3m 14s habana_main
habana_main
January 7, 2025 09:37 3m 14s
fix slow sampling when repetition_penalty is set. (#584) cpu-test #1176: Commit 27a22ab pushed by michalkuligowski
January 7, 2025 09:33 3m 7s habana_main
habana_main
January 7, 2025 09:33 3m 7s
Optimize for topk=1 case if we do not handle duplicates cpu-test #1175: Pull request #603 synchronize by michalkuligowski
January 7, 2025 09:32 3m 10s sarkar/topk1_ignoreduplicates_optimized
sarkar/topk1_ignoreduplicates_optimized
January 7, 2025 09:32 3m 10s
fix slow sampling when repetition_penalty is set. cpu-test #1174: Pull request #584 synchronize by michalkuligowski
January 7, 2025 09:28 3m 13s ccrhx4:make_repetition_penalty_faster_v2
ccrhx4:make_repetition_penalty_faster_v2
January 7, 2025 09:28 3m 13s
Add mark_step for encoder layers cpu-test #1173: Pull request #650 synchronize by michalkuligowski
January 7, 2025 09:18 3m 0s dev/mark_step_for_encoder
dev/mark_step_for_encoder
January 7, 2025 09:18 3m 0s
Device Type HPU support for torch.generator() API cpu-test #1172: Pull request #628 synchronize by nageshdn
January 7, 2025 09:14 Action required nageshdn:habana_main
nageshdn:habana_main
January 7, 2025 09:14 Action required
[BUG fix] Rebase caused spec decode fix (#613) cpu-test #1171: Commit 2d24be7 pushed by michalkuligowski
January 7, 2025 09:06 3m 10s habana_main
habana_main
January 7, 2025 09:06 3m 10s
[BUG fix] Rebase caused spec decode fix cpu-test #1170: Pull request #613 synchronize by xuechendi
January 6, 2025 17:50 3m 9s xuechendi:rebase_caused_spec_decode_fix
xuechendi:rebase_caused_spec_decode_fix
January 6, 2025 17:50 3m 9s
[BUG fix] Rebase caused spec decode fix cpu-test #1169: Pull request #613 synchronize by xuechendi
January 6, 2025 17:37 3m 7s xuechendi:rebase_caused_spec_decode_fix
xuechendi:rebase_caused_spec_decode_fix
January 6, 2025 17:37 3m 7s