Skip to content

Pull requests: vllm-project/vllm-gaudi

New pull request New
58 Open 510 Closed
58 Open 510 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

Doc changes from main to 0.10.2
#574 opened Nov 14, 2025 by mhelf-intel Loading…
1
Nixl deployment fixes documentation Improvements or additions to documentation skip-gaudi-tests
#573 opened Nov 14, 2025 by PatrykWo Loading…
5
Add docker cmdline options to handle long context
#572 opened Nov 14, 2025 by nngokhale • Draft
2
Specify output tensor in matmul_qk - with version difference
#571 opened Nov 14, 2025 by adobrzyn Loading…
7
[Docs] Readme for bucketing from file + env var added (#545) documentation Improvements or additions to documentation skip-gaudi-tests
#570 opened Nov 14, 2025 by adobrzyn Loading…
4
Implementing softmax_fa2 in partial_attn shared and causal
#566 opened Nov 13, 2025 by ksmusz • Draft
6
Docs: Missing content from Habana docs documentation Improvements or additions to documentation skip-gaudi-tests
#562 opened Nov 13, 2025 by mhelf-intel Loading…
8
Add support for chunked attention
#560 opened Nov 12, 2025 by jkaniecki Loading…
14
Add a plugin for variable support in Markdown documentation Improvements or additions to documentation skip-gaudi-tests
#554 opened Nov 12, 2025 by mhelf-intel Loading…
4
fix loading fp8 static quantized model for compressored_tensors format.
#552 opened Nov 11, 2025 by lkk12014402 Loading…
32
Prepare Unified Attention biases on HPU + add NumPy memory pooling
#550 opened Nov 7, 2025 by kzawora-intel Loading…
20
Refactor part of spec decode structure identical to vLLM
#544 opened Nov 7, 2025 by jerrychenhf Loading…
22
Michalkuligowski patch 7
#542 opened Nov 6, 2025 by michalkuligowski • Draft
4
[SW-228042] Add support for dynamic vLLM kv-cache quantization
#538 opened Nov 6, 2025 by dudilester Loading…
11
[Attention Metadata Overhaul 2/N] Move metadata processing outside HPUModelAdapter, prepare biases on CPU
#530 opened Nov 5, 2025 by kzawora-intel Loading…
16
[Attention Metadata Overhaul 1/N] Extract metadata update to HPUAttentionMetadataProcessor
#526 opened Nov 5, 2025 by kzawora-intel Loading…
10
enable lmcache
#521 opened Nov 5, 2025 by hsubramony Loading…
6
reduce graph recompilations in input embeddings for Gemma3
#519 opened Nov 4, 2025 by skaulintel • Draft
7
Call shutdown_inc to mitiagate driver worker teardown order
#511 opened Nov 3, 2025 by michalkuligowski • Draft
1
Udpate TESTOWNERS
#495 opened Oct 28, 2025 by jbyczkow Loading…
4
Initial Commit GPT-OSS
#485 opened Oct 28, 2025 by hlahkar Loading…
9
[SW-242794] Fix not warmed up decode buckets
#484 opened Oct 28, 2025 by jbyczkow • Draft
1
[Attention Metadata Overhaul 3/N] Add per-layer attention metadata
#475 opened Oct 24, 2025 by kzawora-intel • Draft
8
Fix requirements filtering in HPU Dockerfiles
#455 opened Oct 23, 2025 by jakub-sochacki Loading…
6
Enable triangular mask with valid_seq_lengths
#454 opened Oct 23, 2025 by kamil-kaczor Loading…
1
ProTip! no:milestone will show everything without a milestone.