Skip to content

Pull requests: HabanaAI/vllm-fork

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Sort

Pull requests list

Set vllm-hpu-extension revision to bf51134
#1291 opened May 21, 2025 by iboiko-habana Loading…
Add torch.compile tests into test_config.yaml
#1289 opened May 21, 2025 by kzawora-intel Loading…
test disagg 2 nodes
#1283 opened May 20, 2025 by libinta Draft
Qwen2.5 omni
#1269 opened May 19, 2025 by wenbinc-Bin Loading…
Enable triangular attention
#1268 opened May 16, 2025 by kamil-kaczor Draft
Allow FSDPA for Qwen
#1267 opened May 16, 2025 by madamczyk-intel Draft
[draft] Dev flags overhaul
#1266 opened May 16, 2025 by madamczyk-intel Draft
Add split_qkv for Granite
#1263 opened May 15, 2025 by kdamaszk Loading…
set enable-expert-parallel for qwen3-235b FP run
#1257 opened May 14, 2025 by ccrhx4 Loading…
Added embedding online/offline benchmark funtonality
#1253 opened May 13, 2025 by yeonsily Loading…
Enable embedding test on jenkins
#1234 opened May 8, 2025 by yeonsily Loading…
[Qwen3] Enable on HPU
#1227 opened May 8, 2025 by xuechendi Draft
Rebase may 07
#1220 opened May 7, 2025 by michalkuligowski Loading…
Porting alibi fix PR from Haihao and Tanner
#1214 opened May 7, 2025 by testdig Loading…
add calibration files of 235B model on G2
#1201 opened May 6, 2025 by mengniwang95 Loading…
adding the benchmark script
#1191 opened Apr 30, 2025 by mrezavand Loading…
[DRAFT] 3d warmup
#1178 opened Apr 29, 2025 by iboiko-habana Draft
Update README
#1177 opened Apr 29, 2025 by Chris-Sigopt Loading…
ProTip! Exclude everything labeled bug with -label:bug.