Skip to content

Actions: HabanaAI/vllm-fork

Actions

yapf

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
yapf.yml
1,347 workflow runs
1,347 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Fix model OOM issue in llama-405 and mixtral - 2nd attempt yapf #1435: Pull request #644 synchronize by michalkuligowski
January 13, 2025 06:39 1m 52s dev/afierka/fix-oom-loading-weights
dev/afierka/fix-oom-loading-weights
January 13, 2025 06:39 1m 52s
Adds LoRA tests to vLLM CI pipeline yapf #1434: Pull request #680 synchronize by rsshaik1
January 13, 2025 05:11 1m 56s CI_tests_LoRA
CI_tests_LoRA
January 13, 2025 05:11 1m 56s
Adds LoRA tests to vLLM CI pipeline yapf #1433: Pull request #680 synchronize by rsshaik1
January 13, 2025 04:26 1m 55s CI_tests_LoRA
CI_tests_LoRA
January 13, 2025 04:26 1m 55s
Adds LoRA tests to vLLM CI pipeline yapf #1432: Pull request #680 opened by rsshaik1
January 13, 2025 03:37 1m 49s CI_tests_LoRA
CI_tests_LoRA
January 13, 2025 03:37 1m 49s
Add inc fp8 qunatization documentation yapf #1431: Pull request #635 synchronize by nirda7
January 13, 2025 01:31 1m 45s fp8_quantization_documentation
fp8_quantization_documentation
January 13, 2025 01:31 1m 45s
Handle LoRA specific changes in MSS (#675) yapf #1430: Commit c5975f8 pushed by vivekgoe
January 11, 2025 05:54 1m 45s habana_main
habana_main
January 11, 2025 05:54 1m 45s
Fix: selecting correct backend for MultiHeadAttention yapf #1429: Pull request #645 synchronize by adobrzyniewicz-habana
January 10, 2025 15:10 1m 52s adobrzyniewicz/backend_select_fix
adobrzyniewicz/backend_select_fix
January 10, 2025 15:10 1m 52s
Jan 10 rebase yapf #1428: Pull request #677 synchronize by kzawora-intel
January 10, 2025 15:00 1m 57s private/kzawora/jan_10_rebase
private/kzawora/jan_10_rebase
January 10, 2025 15:00 1m 57s
Jan 10 rebase yapf #1427: Pull request #677 opened by kzawora-intel
January 10, 2025 14:42 2m 1s private/kzawora/jan_10_rebase
private/kzawora/jan_10_rebase
January 10, 2025 14:42 2m 1s
WA for OOM in qwen 2 - sync after loading weights yapf #1426: Pull request #398 synchronize by michalkuligowski
January 10, 2025 10:29 1m 54s michalkuligowski-qwen-sync_after_weightload
michalkuligowski-qwen-sync_after_weightload
January 10, 2025 10:29 1m 54s
Fix for random sampler recompilations for incomplete batches yapf #1425: Pull request #663 synchronize by mfylcek
January 10, 2025 08:59 1m 49s dev/mfylcek/sampler-aware_batch_size_padding
dev/mfylcek/sampler-aware_batch_size_padding
January 10, 2025 08:59 1m 49s
Handle LoRA specific changes in MSS yapf #1423: Pull request #675 opened by SanjuCSudhakaran
January 10, 2025 07:48 2m 2s lora-mss
lora-mss
January 10, 2025 07:48 2m 2s
Add inc fp8 qunatization documentation yapf #1422: Pull request #635 synchronize by nirda7
January 9, 2025 13:17 1m 57s fp8_quantization_documentation
fp8_quantization_documentation
January 9, 2025 13:17 1m 57s
[SW-197036] - use torch._scaled_mm with hpu (#660) yapf #1421: Commit 73aaf71 pushed by nirda7
January 9, 2025 13:15 1m 56s habana_main
habana_main
January 9, 2025 13:15 1m 56s
Add inc fp8 qunatization documentation yapf #1420: Pull request #635 synchronize by nirda7
January 9, 2025 11:35 2m 4s fp8_quantization_documentation
fp8_quantization_documentation
January 9, 2025 11:35 2m 4s
WA for OOM in qwen 2 - sync after loading weights yapf #1419: Pull request #398 synchronize by michalkuligowski
January 9, 2025 11:30 2m 3s michalkuligowski-qwen-sync_after_weightload
michalkuligowski-qwen-sync_after_weightload
January 9, 2025 11:30 2m 3s
Add inc fp8 qunatization documentation yapf #1418: Pull request #635 synchronize by nirda7
January 9, 2025 11:27 1m 45s fp8_quantization_documentation
fp8_quantization_documentation
January 9, 2025 11:27 1m 45s
WA for OOM in qwen 2 - sync after loading weights yapf #1417: Pull request #398 synchronize by michalkuligowski
January 9, 2025 11:23 1m 48s michalkuligowski-qwen-sync_after_weightload
michalkuligowski-qwen-sync_after_weightload
January 9, 2025 11:23 1m 48s
WA for OOM in qwen 2 - sync after loading weights yapf #1416: Pull request #398 synchronize by michalkuligowski
January 9, 2025 11:22 2m 0s michalkuligowski-qwen-sync_after_weightload
michalkuligowski-qwen-sync_after_weightload
January 9, 2025 11:22 2m 0s
[SW-197036] - use torch._scaled_mm with hpu yapf #1415: Pull request #660 synchronize by nirda7
January 9, 2025 09:49 1m 48s remove_scaled_mm_wa
remove_scaled_mm_wa
January 9, 2025 09:49 1m 48s
Multimodality fix for llava yapf #1414: Pull request #641 synchronize by adobrzyniewicz-habana
January 9, 2025 07:53 1m 44s adobrzyniewicz/multimodality_for_llava
adobrzyniewicz/multimodality_for_llava
January 9, 2025 07:53 1m 44s
add renormalize param for FusedMOE yapf #1413: Pull request #671 opened by tangleintel
January 9, 2025 06:22 Action required tangleintel:lei/upstream/add_renormalize_param_4_moe
tangleintel:lei/upstream/add_renormalize_param_4_moe
January 9, 2025 06:22 Action required
Limit number of dummy cross attention blocks (#667) yapf #1412: Commit fa9dbf2 pushed by michalkuligowski
January 8, 2025 17:07 1m 56s habana_main
habana_main
January 8, 2025 17:07 1m 56s
[SW-197036] - use torch._scaled_mm with hpu yapf #1411: Pull request #660 synchronize by nirda7
January 8, 2025 16:29 1m 56s remove_scaled_mm_wa
remove_scaled_mm_wa
January 8, 2025 16:29 1m 56s
Use FusedSDPA for MllamaVisionSdpaAttention (#620) yapf #1410: Commit cccf363 pushed by michalkuligowski
January 8, 2025 16:28 1m 49s habana_main
habana_main
January 8, 2025 16:28 1m 49s