Skip to content

Pull requests: HabanaAI/vllm-fork

New pull request New
42 Open 627 Closed
42 Open 627 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Adopt PyTorch dynamo cache size to current layer definition
#733 opened Jan 23, 2025 by anko-intel Loading…
[WIP] Pipeline Parallelism implementation.
#731 opened Jan 23, 2025 by jmaksymczuk • Draft
Make sure that all workers are notified about end of execution loop
#730 opened Jan 23, 2025 by kdamaszk Loading…
1
[BLOCKER] Fix in v1.19.0 for dataclass error due to triton package update
#729 opened Jan 23, 2025 by MohitIntel Loading…
[BLOCKER] Fix in v1.19.1 for dataclass error due to triton package update
#727 opened Jan 23, 2025 by MohitIntel Loading…
[BLOCKER] Fix in v1.19.2 for dataclass error due to triton package update
#726 opened Jan 23, 2025 by MohitIntel Loading…
Add interleave sliding window by using fusedsdpa kernel.
#725 opened Jan 22, 2025 by libinta Loading…
Allow tests to run in t.compile
#724 opened Jan 22, 2025 by Kacper-Pietkun Loading…
[DONOTMERGE] check fake-hpu build num
#722 opened Jan 22, 2025 by madamczykhabana • Draft
Delayed sampling
#720 opened Jan 22, 2025 by mfylcek • Draft
make benchmark_throughput static support single image input
#718 opened Jan 22, 2025 by yma11 • Draft
Support for multi step scheduling in enc dec models
#715 opened Jan 21, 2025 by jkaniecki Loading…
2
Rebase 2025.01.21 rebase
#714 opened Jan 21, 2025 by kzawora-intel Loading…
Fix LoRA test
#711 opened Jan 21, 2025 by SanjuCSudhakaran Loading…
[SW-216341] hotfix - Revert vllm/attention/layer.py changes from 0f8cafe - fix torch.compile recompilations
#709 opened Jan 20, 2025 by RafLit Loading…
multi-image support for llama3.2
#705 opened Jan 20, 2025 by yma11 Loading…
add force_greedy_sample
#704 opened Jan 20, 2025 by jikunshang Loading…
Rebase 2025-01-19
#703 opened Jan 19, 2025 by kzawora-intel Loading…
Add pip upgrade to installation steps
#699 opened Jan 17, 2025 by michalkuligowski Loading…
[WIP] Merge lazy and t.compile jenkins tests
#693 opened Jan 16, 2025 by afierka-intel Loading…
Enabled and optimized GLM-4v-9b on Gaudi
#691 opened Jan 16, 2025 by gyou2021 Loading…
Bump jinja2 from 3.1.4 to 3.1.5 dependencies Pull requests that update a dependency file
#679 opened Jan 12, 2025 by dependabot bot Loading…
add renormalize param for FusedMOE
#671 opened Jan 9, 2025 by tangleintel Loading…
2
Draft: Delayed prompts
#659 opened Dec 20, 2024 by kamil-kaczor • Draft
Chunked Prefill
#656 opened Dec 20, 2024 by hlahkar • Draft
ProTip! Follow long discussions with comments:>50.