Skip to content

Pull requests: vllm-project/vllm-gaudi

New pull request New
31 Open 102 Closed
31 Open 102 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] Fully overlap model execution
#134 opened Sep 3, 2025 by tianmu-li • Draft
Unified Attention POC
#133 opened Sep 3, 2025 by madamczyk-intel • Draft
Disable warmup for defragmentator
#132 opened Sep 3, 2025 by mswiniarsk Loading…
1
Introducing sampler warmup as separate warmup step
#131 opened Sep 3, 2025 by ksmusz Loading…
2
Increase allowed line length to 120 + reformat accordingly
#130 opened Sep 3, 2025 by kzawora-intel Loading…
1
WIP enabling llama4 models
#128 opened Sep 3, 2025 by afierka-intel • Draft
Merging vllm docker implementation to vllm-gaudi (v1)
#125 opened Sep 2, 2025 by PatrykWo Loading…
Enable synchronized weight loader
#123 opened Sep 2, 2025 by kamil-kaczor • Draft
Do not add max_blocks as a bucket in linear bucketing with cpa
#121 opened Sep 2, 2025 by mswiniarsk Loading…
Enable embedding feature
#120 opened Sep 2, 2025 by slokesha Loading…
2
Add out-of-tree HPU schedulers
#119 opened Sep 1, 2025 by kzawora-intel Loading…
[WARMUP] fix update bucket
#118 opened Aug 29, 2025 by xuechendi Loading…
[Bucketing] WA for warmup big values - crash
#116 opened Aug 29, 2025 by adobrzyn Loading…
1
Extract synapse driver version from hl-smi
#115 opened Aug 29, 2025 by michalkuligowski • Draft
Re-quantize FP8 model with INC
#114 opened Aug 29, 2025 by yiliu30 • Draft
Add tests for custom op registration
#109 opened Aug 28, 2025 by Kacper-Pietkun Loading…
2
Fix warmup break when max decode bucket bs > max num seq
#107 opened Aug 26, 2025 by taran2210 Loading…
7
[Merged Prefill] Warmup for merged prefill
#104 opened Aug 26, 2025 by adobrzyn Loading…
9
[Bucketing] Read buckets from file
#101 opened Aug 23, 2025 by adobrzyn • Draft
initial port for nixl
#100 opened Aug 22, 2025 by hsubramony Loading…
9
Enable sampler compilation
#95 opened Aug 22, 2025 by Kacper-Pietkun • Draft
1
Add data parallel support
#80 opened Aug 14, 2025 by wuxun-zhang Loading…
3 tasks done
18
Add attention unit tests
#74 opened Aug 12, 2025 by tthaddey Loading…
4
Lookahead decoding
#72 opened Aug 11, 2025 by jkaniecki Loading…
Fixed Plugin Test
#70 opened Aug 8, 2025 by slokesha Loading…
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.