Skip to content

Actions: microsoft/DeepSpeed

Actions

hpu-gaudi2

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
hpu-gaudi2.yml
1,204 workflow runs
1,204 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Stage3: Use new torch grad accumulation hooks API hpu-gaudi2 #1408: Pull request #6773 synchronize by loadams
December 19, 2024 20:32 55m 51s deepcharm:stage3-use-new-grad-acc-api
deepcharm:stage3-use-new-grad-acc-api
December 19, 2024 20:32 55m 51s
Zero2: avoid graph breaks in torch.compile by using param_idx hpu-gaudi2 #1407: Pull request #6803 synchronize by loadams
December 19, 2024 17:36 56m 24s nelyahu:zero2_param_idx
nelyahu:zero2_param_idx
December 19, 2024 17:36 56m 24s
hpu_accelerator: use torch.use_deterministic_algorithms hpu-gaudi2 #1406: Pull request #6897 opened by nelyahu
December 19, 2024 07:23 57m 28s nelyahu:patch-2
nelyahu:patch-2
December 19, 2024 07:23 57m 28s
hpu-gaudi2 hpu-gaudi2 #1405: Scheduled
December 19, 2024 00:12 1h 58m 41s master
master
December 19, 2024 00:12 1h 58m 41s
Stage3: Use new torch grad accumulation hooks API hpu-gaudi2 #1404: Pull request #6773 synchronize by loadams
December 18, 2024 17:55 1h 50m 9s deepcharm:stage3-use-new-grad-acc-api
deepcharm:stage3-use-new-grad-acc-api
December 18, 2024 17:55 1h 50m 9s
Zero2: avoid graph breaks in torch.compile by using param_idx hpu-gaudi2 #1403: Pull request #6803 synchronize by loadams
December 18, 2024 17:55 55m 9s nelyahu:zero2_param_idx
nelyahu:zero2_param_idx
December 18, 2024 17:55 55m 9s
Stage3: Use new torch grad accumulation hooks API hpu-gaudi2 #1402: Pull request #6773 synchronize by loadams
December 18, 2024 16:51 1h 4m 35s deepcharm:stage3-use-new-grad-acc-api
deepcharm:stage3-use-new-grad-acc-api
December 18, 2024 16:51 1h 4m 35s
Zero2: avoid graph breaks in torch.compile by using param_idx hpu-gaudi2 #1401: Pull request #6803 synchronize by loadams
December 18, 2024 16:51 57m 55s nelyahu:zero2_param_idx
nelyahu:zero2_param_idx
December 18, 2024 16:51 57m 55s
Use ds-specific module id to avoid conflicts hpu-gaudi2 #1399: Pull request #6847 synchronize by tjruwase
December 18, 2024 13:59 51m 3s olruwase/pr_6772
olruwase/pr_6772
December 18, 2024 13:59 51m 3s
Stage3: Use new torch grad accumulation hooks API hpu-gaudi2 #1398: Pull request #6773 synchronize by deepcharm
December 18, 2024 09:44 55m 44s deepcharm:stage3-use-new-grad-acc-api
deepcharm:stage3-use-new-grad-acc-api
December 18, 2024 09:44 55m 44s
Add arctic model support by adding w2 to all_reduce hpu-gaudi2 #1397: Pull request #6856 synchronize by loadams
December 18, 2024 01:31 6h 27m 1s pi314ever:arctic-enabling-upstream
pi314ever:arctic-enabling-upstream
December 18, 2024 01:31 6h 27m 1s
hpu-gaudi2 hpu-gaudi2 #1396: Scheduled
December 18, 2024 00:11 6h 50m 59s master
master
December 18, 2024 00:11 6h 50m 59s
Zero2: avoid graph breaks in torch.compile by using param_idx hpu-gaudi2 #1395: Pull request #6803 synchronize by loadams
December 17, 2024 20:22 1h 51m 8s nelyahu:zero2_param_idx
nelyahu:zero2_param_idx
December 17, 2024 20:22 1h 51m 8s
Add arctic model support by adding w2 to all_reduce hpu-gaudi2 #1394: Pull request #6856 synchronize by loadams
December 17, 2024 19:58 57m 18s pi314ever:arctic-enabling-upstream
pi314ever:arctic-enabling-upstream
December 17, 2024 19:58 57m 18s
[inf] Add config var to enable keeping module on host hpu-gaudi2 #1392: Pull request #6846 synchronize by oelayan7
December 17, 2024 07:46 55m 40s oelayan7:keep_module_on_host
oelayan7:keep_module_on_host
December 17, 2024 07:46 55m 40s
[inf] Add config var to enable keeping module on host hpu-gaudi2 #1391: Pull request #6846 synchronize by oelayan7
December 17, 2024 07:39 Action required oelayan7:keep_module_on_host
oelayan7:keep_module_on_host
December 17, 2024 07:39 Action required
Add arctic model support by adding w2 to all_reduce hpu-gaudi2 #1390: Pull request #6856 synchronize by tjruwase
December 17, 2024 01:35 55m 25s pi314ever:arctic-enabling-upstream
pi314ever:arctic-enabling-upstream
December 17, 2024 01:35 55m 25s
hpu-gaudi2 hpu-gaudi2 #1389: Scheduled
December 17, 2024 00:12 1h 58m 59s master
master
December 17, 2024 00:12 1h 58m 59s
Zero2: avoid graph breaks in torch.compile by using param_idx hpu-gaudi2 #1388: Pull request #6803 synchronize by loadams
December 16, 2024 22:52 55m 57s nelyahu:zero2_param_idx
nelyahu:zero2_param_idx
December 16, 2024 22:52 55m 57s
Zero2: avoid graph breaks in torch.compile by using param_idx hpu-gaudi2 #1387: Pull request #6803 synchronize by loadams
December 16, 2024 22:15 1m 17s nelyahu:zero2_param_idx
nelyahu:zero2_param_idx
December 16, 2024 22:15 1m 17s
Support pure meta model lm_head tp hpu-gaudi2 #1386: Pull request #6812 synchronize by loadams
December 16, 2024 19:34 55m 6s Yejing-Lai:lyj/lm_head_replace
Yejing-Lai:lyj/lm_head_replace
December 16, 2024 19:34 55m 6s
Add MLP/lm_head tp grain size setting. hpu-gaudi2 #1385: Pull request #6828 synchronize by loadams
December 16, 2024 19:33 1h 50m 53s Yejing-Lai:lyj/tp_grain_size
Yejing-Lai:lyj/tp_grain_size
December 16, 2024 19:33 1h 50m 53s
Add arctic model support by adding w2 to all_reduce hpu-gaudi2 #1384: Pull request #6856 synchronize by tjruwase
December 16, 2024 12:24 54m 45s pi314ever:arctic-enabling-upstream
pi314ever:arctic-enabling-upstream
December 16, 2024 12:24 54m 45s
hpu-gaudi2 hpu-gaudi2 #1383: Scheduled
December 16, 2024 00:12 1h 55m 7s master
master
December 16, 2024 00:12 1h 55m 7s
Stage3: Use new torch grad accumulation hooks API hpu-gaudi2 #1382: Pull request #6773 synchronize by deepcharm
December 15, 2024 12:43 Action required deepcharm:stage3-use-new-grad-acc-api
deepcharm:stage3-use-new-grad-acc-api
December 15, 2024 12:43 Action required