Skip to content

Pull requests: HabanaAI/vllm-fork

New pull request New
28 Open 380 Closed
28 Open 380 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

[BugFix][Habana_main][Multistep]Fix multistep deepcopy overhead
#452 opened Nov 1, 2024 by xuechendi Loading…
1
Config hidden layer number to run in 1 lazy graph
#451 opened Nov 1, 2024 by libinta Loading…
[CI] Add Llama2 to torch compile tests
#446 opened Oct 30, 2024 by anko-intel Loading…
3
Add multi step scheduling scenario to jenkins CI
#445 opened Oct 30, 2024 by afierka-intel • Draft
Fix branch version in README_GAUDI.md
#444 opened Oct 29, 2024 by michalkuligowski Loading…
to make repetition penalty faster
#442 opened Oct 29, 2024 by ccrhx4 Loading…
4
Add models-tiny CI step with Llama3.2-1B
#440 opened Oct 28, 2024 by kzawora-intel • Draft
Oct 28 rebase
#439 opened Oct 28, 2024 by kzawora-intel Loading…
Resolved alibi bias issue by reverting to PA v1.
#438 opened Oct 28, 2024 by tannervoas742 Loading…
1
Resolved alibi bias issue due to porting flat PA pr
#437 opened Oct 28, 2024 by tannervoas742 Loading…
1
Add HPU information to collect_env script
#430 opened Oct 25, 2024 by michalkuligowski Loading…
1
fix profiler end for prepare_input_tensor
#422 opened Oct 24, 2024 by jikunshang Loading…
1
GPTQ Support
#421 opened Oct 23, 2024 by maktukmak Loading…
Add DeepSeek-V2-Lite/DeepSeek-V2-Lite-Chat model support
#410 opened Oct 21, 2024 by hlin99 Loading…
4
[PoC] Add max padding ratio to padding aware scheduler
#407 opened Oct 18, 2024 by kzawora-intel • Draft
Create run-lm-eval-mmlu.sh
#399 opened Oct 16, 2024 by michalkuligowski • Draft
WA for OOM in qwen 2 - sync after loading weights
#398 opened Oct 16, 2024 by michalkuligowski Loading…
[bucketing overhaul 2/n] Delegate bucket management to HPUBucketingContext
#395 opened Oct 15, 2024 by kzawora-intel Loading…
1
fix hpu destructors flow and remove finish_measurements
#379 opened Oct 10, 2024 by nirda7 Loading…
5
[New Feature][Habana-Main] speculative_decoding HPU support
#375 opened Oct 8, 2024 by xuechendi Loading…
21
Add bucket calibration, allow reading/writing bucketing configs to file
#345 opened Sep 27, 2024 by kzawora-intel Loading…
5
[DO NOT MERGE] Upstream test PR
#322 opened Sep 23, 2024 by kzawora-intel Loading…
Optimize LoRA mask creation habana Issues or PRs submitted by Habana Labs
#285 opened Sep 13, 2024 by SanjuCSudhakaran • Draft
1
Draft: Add max-num-prefill-seqs parameter habana Issues or PRs submitted by Habana Labs
#253 opened Sep 6, 2024 by kzawora-intel • Draft
2
enabling multi-node serving on Gaudi ray cluster intel Issues or PRs submitted by Intel
#218 opened Aug 29, 2024 by vishnumadhu365 Loading…
2
ProTip! What’s not been updated in a month: updated:<2024-10-01.