Skip to content

Actions: HabanaAI/vllm-fork

Cleanup PR Body

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
300 workflow runs
300 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[SW-216666] - add fp8 to the hpu supported quantization list
Cleanup PR Body #300: Pull request #739 opened by nirda7
January 26, 2025 19:43 17s
January 26, 2025 19:43 17s
Pipeline Parallelism implementation.
Cleanup PR Body #299: Pull request #731 edited by jmaksymczuk
January 24, 2025 14:04 13s
January 24, 2025 14:04 13s
hotfix - Revert vllm/attention/layer.py changes from 0f8cafe - fix torch.compile recompilations
Cleanup PR Body #298: Pull request #709 edited by anko-intel
January 24, 2025 09:51 18s
January 24, 2025 09:51 18s
Adopt dynamo cache size to current layer definition
Cleanup PR Body #297: Pull request #737 edited by anko-intel
January 24, 2025 08:18 12s
January 24, 2025 08:18 12s
Adopt dynamo cache size to current layer definition
Cleanup PR Body #296: Pull request #737 opened by anko-intel
January 24, 2025 08:16 20s
January 24, 2025 08:16 20s
Update CODEOWNERS
Cleanup PR Body #295: Pull request #736 opened by szutenberg
January 24, 2025 05:46 13s
January 24, 2025 05:46 13s
TP parallel seq_len
Cleanup PR Body #294: Pull request #735 opened by tianmu-li
January 24, 2025 00:33 16s
January 24, 2025 00:33 16s
Multimodal placeholder WA
Cleanup PR Body #293: Pull request #734 opened by adobrzyniewicz-habana
January 23, 2025 18:57 18s
January 23, 2025 18:57 18s
Pipeline Parallelism implementation.
Cleanup PR Body #292: Pull request #731 opened by jmaksymczuk
January 23, 2025 14:00 14s
January 23, 2025 14:00 14s
Make sure that all workers are notified about end of execution loop
Cleanup PR Body #291: Pull request #730 opened by kdamaszk
January 23, 2025 10:00 17s
January 23, 2025 10:00 17s
[BLOCKER] Fix in v1.19.0 for dataclass error due to triton package update
Cleanup PR Body #290: Pull request #729 opened by MohitIntel
January 23, 2025 04:35 13s
January 23, 2025 04:35 13s
Pin triton to v3.1.0 for HPU
Cleanup PR Body #289: Pull request #728 opened by tannervoas742
January 23, 2025 04:27 15s
January 23, 2025 04:27 15s
[BLOCKER] Fix in v1.19.1 for dataclass error due to triton package update
Cleanup PR Body #288: Pull request #727 opened by MohitIntel
January 23, 2025 04:26 14s
January 23, 2025 04:26 14s
[BLOCKER] Fix in v1.19.2 for dataclass error due to triton package update
Cleanup PR Body #287: Pull request #726 edited by MohitIntel
January 23, 2025 04:25 13s
January 23, 2025 04:25 13s
[BLOCKER] Fix in v1.19.2 for dataclass error due to triton package update
Cleanup PR Body #286: Pull request #726 edited by MohitIntel
January 23, 2025 04:22 13s
January 23, 2025 04:22 13s
[BLOCKER] Fix in v1.19.2 for dataclass error due to triton package update
Cleanup PR Body #285: Pull request #726 opened by MohitIntel
January 23, 2025 04:21 14s
January 23, 2025 04:21 14s
Add interleave sliding window by using fusedsdpa kernel.
Cleanup PR Body #284: Pull request #725 opened by libinta
January 22, 2025 20:58 15s
January 22, 2025 20:58 15s
Allow tests to run in t.compile
Cleanup PR Body #283: Pull request #724 opened by Kacper-Pietkun
January 22, 2025 13:13 13s
January 22, 2025 13:13 13s
[Draft] Create update_requirements_sha
Cleanup PR Body #282: Pull request #723 edited by michalkuligowski
January 22, 2025 12:20 12s
January 22, 2025 12:20 12s
[Draft] Create update_requirements_sha
Cleanup PR Body #281: Pull request #723 opened by michalkuligowski
January 22, 2025 12:17 15s
January 22, 2025 12:17 15s
[DONOTMERGE] check fake-hpu build num
Cleanup PR Body #280: Pull request #722 opened by madamczykhabana
January 22, 2025 11:06 15s
January 22, 2025 11:06 15s
[SW-199650] Add HPU fp8 DynamicMOE Op
Cleanup PR Body #279: Pull request #721 opened by dudilester
January 22, 2025 10:22 16s
January 22, 2025 10:22 16s
Delayed sampling
Cleanup PR Body #278: Pull request #720 opened by mfylcek
January 22, 2025 09:32 21s
January 22, 2025 09:32 21s
make benchmark_throughput static support single image input
Cleanup PR Body #277: Pull request #718 opened by yma11
January 22, 2025 02:51 20s
January 22, 2025 02:51 20s
update datatype - seems this can fix the acc issue
Cleanup PR Body #276: Pull request #717 opened by xuechendi
January 21, 2025 22:06 19s
January 21, 2025 22:06 19s