Skip to content

Pull requests: vllm-project/vllm-gaudi

New pull request New
58 Open 337 Closed
58 Open 337 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] Unified Attention - partial batch persistence
#400 opened Oct 13, 2025 by kzawora-intel • Draft
2
Unified Attention - High Level Profiler Integration
#399 opened Oct 13, 2025 by kzawora-intel Loading…
1
Change max bucket while using conti pa + defrag
#397 opened Oct 13, 2025 by adobrzyn Loading…
1
Use query in linear flags - seq as fallback option
#396 opened Oct 13, 2025 by adobrzyn Loading…
12
Minor optimizationm for bucketing calc
#395 opened Oct 13, 2025 by michalkuligowski Loading…
4
Sampling with rep penalty wa
#394 opened Oct 13, 2025 by michalkuligowski • Draft
1
Unified Attention Accuracy Bugfixes
#393 opened Oct 13, 2025 by kzawora-intel Loading…
1
Docs installation, quick start and build fixes (#384) documentation Improvements or additions to documentation skip-gaudi-tests
#392 opened Oct 13, 2025 by PatrykWo Loading…
Fix typo in installation.md: correct script name to install_nixl.py
#385 opened Oct 10, 2025 by yafshar Loading…
4
Multi-image generation CI tests
#377 opened Oct 10, 2025 by MohitIntel Loading…
4
defrag: tail-compaction that preserves hot-block locality and halves memcpy traffic
#376 opened Oct 9, 2025 by yafshar • Draft
6
Buckets from file - alpha version
#375 opened Oct 9, 2025 by adobrzyn Loading…
2 of 5 tasks
Draft: Add Unified Attention UTs
#374 opened Oct 9, 2025 by kzawora-intel • Draft
4
Add non-unified attention numerics unit tests
#372 opened Oct 9, 2025 by kzawora-intel Loading…
1
Unified attention improvemets
#363 opened Oct 9, 2025 by adobrzyn Loading…
2 tasks done
4
Fix issue with async_scheduling when dealing with chunked input
#360 opened Oct 8, 2025 by tianmu-li Loading…
14
Fix issue with async_scheduling when dealing with chunked input
#359 opened Oct 8, 2025 by tianmu-li Loading…
14
[v0.10.2] update sha, was using v0.10.2rc3 sha due missing of v0.10.2
#356 opened Oct 8, 2025 by xuechendi Loading…
Add missing prompt bucket to warmup, when max_ctx is 0
#352 opened Oct 8, 2025 by iboiko-habana Loading…
3
Unit test for prefix caching in Gaudi plugin
#349 opened Oct 8, 2025 by iirzynska Loading…
5
Update of VLLM_PROMPT_BS_BUCKET_MAX logic, real bs change, not only linear warmup
#348 opened Oct 8, 2025 by iboiko-habana Loading…
11
Cherrypick cd docker fixes/commits from v0.10.2 to v0.11.0
#347 opened Oct 8, 2025 by nngokhale Loading…
1
Install pytorch from habanalabs-installer
#345 opened Oct 8, 2025 by cabelo Loading…
[0.11.0] [SW-241908] Omit all prompt buckets that exceed max_num_batched_tokens (#331) - cherry-pick
#343 opened Oct 8, 2025 by skavulya Loading…
2
[0.10.2] [SW-241908] Omit all prompt buckets that exceed max_num_batched_tokens (#331) - cherry-pick
#342 opened Oct 8, 2025 by skavulya Loading…
3
ProTip! Filter pull requests by the default branch with base:main.