Skip to content

Pull requests: rebellions-sw/vllm-rbln

New pull request New
13 Open 99 Closed
13 Open 99 Closed
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
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

(WIP) feat(model): add paligemma, paligemma2, and gemma2 enhancement New feature or request optimum Optimum based implmenetion
#162 opened Nov 20, 2025 by rebel-eunji Loading…
2 of 12 tasks
@rebel-eunji
feat: mixed precision quantization
#159 opened Nov 18, 2025 by rebel-jaehwang Loading…
4 of 12 tasks
Update torch version from 2.6.0 to 2.8.0
#155 opened Nov 14, 2025 by rebel-jonghewk • Draft
12 tasks
feat(core): add pooling model initial support for V1 engine torch.compile torch.compile based implementation
#152 opened Nov 10, 2025 by pei0033 Loading…
5 of 12 tasks
@pei0033
chore(deps): bump optimum-rbln package from 0.9.2.a7 to 0.9.2(stable)
#149 opened Nov 7, 2025 by rebel-eunji Loading…
1 of 12 tasks
@rebel-eunji
update MoE PoC features & bfloat16 model load torch.compile torch.compile based implementation
#145 opened Nov 4, 2025 by rebel-wonsubkim Loading…
@rebel-wonsubkim
13
ci: add steps for vllm upstream test
#130 opened Oct 24, 2025 by rebel-jaebin Loading…
4 of 12 tasks
@rebel-jaebin
14
ci: add GitHub Actions workflow for ARC CI testing
#120 opened Oct 20, 2025 by rebel-jaebin Loading…
4 of 12 tasks
@rebel-jaebin
86
other: Script for debugging and metrics
#112 opened Oct 16, 2025 by rebel-eunji Loading…
1 of 12 tasks
@rebel-eunji
11
(WIP) feat(core): allow multiple prefill requests to be scheduled in a chunk torch.compile torch.compile based implementation
#88 opened Sep 24, 2025 by kkimmk • Draft
4 of 12 tasks
gha: do not use cuda torch improvements
#67 opened Aug 28, 2025 by dtrifiro • Draft
3
gha: do not use cuda torch
#57 opened Aug 19, 2025 by dtrifiro Loading…
3
Add parameter validation for LLMEngine initialization enhancement New feature or request optimum Optimum based implmenetion
#12 opened Jul 22, 2025 by rebel-eunji • Draft
1 of 9 tasks
3
ProTip! Exclude everything labeled bug with -label:bug.