Skip to content

Pull requests: vllm-project/vllm-gaudi

New pull request New
68 Open 581 Closed
68 Open 581 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

Optimize MoE via chunk settings
#658 opened Nov 28, 2025 by xinyu-intel Loading…
7
Add get_device_total_memory method
#656 opened Nov 28, 2025 by pawel-olejniczak Loading…
1
Fix for links in docker md documentation Improvements or additions to documentation skip-gaudi-tests
#653 opened Nov 27, 2025 by PatrykWo Loading…
1
[FIX_FOR_VLLM_LATEST] Fix the Attention imports
#652 opened Nov 27, 2025 by pawel-olejniczak Loading…
1
[GAUDISW-228042] Add support for dynamic quant with V scales on hidden dim
#650 opened Nov 27, 2025 by dudilester Loading…
8
platform: optimize grouped topk op
#647 opened Nov 27, 2025 by xinyu-intel Loading…
6
make mla weight contiguous
#646 opened Nov 27, 2025 by xinyu-intel Loading…
2
bucket: add query len 1 to prefill bucket
#645 opened Nov 27, 2025 by xinyu-intel Loading…
8
Hybrid KV cache for hpu
#644 opened Nov 26, 2025 by michalkuligowski • Draft
3
Resolve issue with async scheduling when decode and prompt tokens are mixed
#642 opened Nov 26, 2025 by tianmu-li Loading…
4
[CI] GSM8K: don't override lm_eval batch_size & don't disable prefix caching by default
#640 opened Nov 26, 2025 by kzawora-intel Loading…
2
Removing external links from the main page documentation Improvements or additions to documentation skip-gaudi-tests
#638 opened Nov 26, 2025 by PatrykWo Loading…
2
nixl: add lancher and proxy server for PD workloads
#635 opened Nov 26, 2025 by xinyu-intel • Draft
13
Fix filter for edge case & prefill bs > 1
#634 opened Nov 26, 2025 by adobrzyn Loading…
3
Spec decode warmup support
#624 opened Nov 25, 2025 by jerrychenhf Loading…
2
Fix environment setup for FP8
#623 opened Nov 25, 2025 by yiliu30 Loading…
3
Enable dequant fp8 weights quantized per-channel with compressed-tensor method
#621 opened Nov 24, 2025 by mandy-li Loading…
7
enable spec decode for Unified Attention, part1
#619 opened Nov 21, 2025 by xuechendi Loading…
5
Fix transformers version mismatch causing editable install failure
#618 opened Nov 21, 2025 by Saiteja-Garlapati Loading…
2
lora, fix for PR28545
#617 opened Nov 21, 2025 by iboiko-habana Loading…
1
Allow building vllm-plugin docker for ubuntu with upstream torch
#613 opened Nov 21, 2025 by mmuszynskihabana Loading…
1
Sleep mode support
#584 opened Nov 18, 2025 by Kacper-Pietkun Loading…
14
[DOCKER update] update docker to 1.23, transformers to 4.56.0
#580 opened Nov 17, 2025 by xuechendi • Draft
3
Add support of FP32 softmax to unified attention
#577 opened Nov 17, 2025 by afierka-intel • Draft
12
Implementing softmax_fa2 in partial_attn shared and causal
#566 opened Nov 13, 2025 by ksmusz Loading…
19
ProTip! Mix and match filters to narrow down what you’re looking for.