Skip to content

Pull requests: vllm-project/vllm-gaudi

New pull request New
61 Open 443 Closed
61 Open 443 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

[SW-243111] Add correctors for decode buckets
#509 opened Oct 31, 2025 by jbyczkow Loading…
1
[New Feature] Add cpu core pinning to vllm-server to improve performance.
#502 opened Oct 29, 2025 by louie-tsai Loading…
21
Port: Fix bucketing of query + num_blocks neighbor expansion #350, #355
#500 opened Oct 29, 2025 by iboiko-habana Loading…
4
DP: allreduce on the host
#498 opened Oct 29, 2025 by xinyu-intel Loading…
2
Udpate TESTOWNERS
#495 opened Oct 28, 2025 by jbyczkow Loading…
4
Documentation updates - part 1 documentation Improvements or additions to documentation skip-gaudi-tests
#493 opened Oct 28, 2025 by mhelf-intel Loading…
29
Initial Commit GPT-OSS
#485 opened Oct 28, 2025 by hlahkar Loading…
[SW-242794] Fix not warmed up decode buckets
#484 opened Oct 28, 2025 by jbyczkow • Draft
1
[SW-242523] Support per-tensor FP8 scaling
#483 opened Oct 27, 2025 by skavulya Loading…
14
Port "[Bugfix] Fix bucketing of query + num_blocks neighbor expansion" #350
#482 opened Oct 27, 2025 by iboiko-habana Loading…
2
Fix docker cmdlines for v0.10.2_next workarounds
#477 opened Oct 25, 2025 by nngokhale Loading…
2
[Attention Metadata Overhaul 1/N] Add per-layer attention metadata
#475 opened Oct 24, 2025 by kzawora-intel • Draft
8
Simplify requirements
#458 opened Oct 23, 2025 by pawel-olejniczak Loading…
8
Add tests for custom operator implementation correctness
#457 opened Oct 23, 2025 by Kacper-Pietkun Loading…
8
Fix requirements filtering in HPU Dockerfiles
#455 opened Oct 23, 2025 by jakub-sochacki Loading…
5
Enable triangular mask with valid_seq_lengths
#454 opened Oct 23, 2025 by kamil-kaczor Loading…
1
Remove VLLM_DELAYED_SAMPLING
#433 opened Oct 21, 2025 by xwu-intel Loading…
2
Automatically adjust VLLM_DECODE_BLOCK_BUCKET_MIN if it exceeds max_blocks
#432 opened Oct 20, 2025 by dsocek Loading…
10
enable gdr on 10.2 baseline
#431 opened Oct 20, 2025 by hsubramony • Draft
20
Fix for Llama4 static quantization
#430 opened Oct 20, 2025 by vidyasiv Loading…
2
Implementing softmax kernels in partial_attn_unique
#429 opened Oct 20, 2025 by ksmusz • Draft
4
multimodal support for unified attn
#423 opened Oct 19, 2025 by attafosu Loading…
7
initial port for heterogenous support
#420 opened Oct 17, 2025 by hsubramony • Draft
2
Fix docker cmdlines for v.0.11.0 work arounds
#417 opened Oct 17, 2025 by nngokhale Loading…
2
Add async scheduling for unified attention
#414 opened Oct 16, 2025 by tianmu-li Loading…
8
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.