Skip to content

Pull requests: HabanaAI/vllm-fork

New pull request New
40 Open 773 Closed
40 Open 773 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

Cherry-pick of: "Delayed sampling tp fix #834"
#885 opened Mar 4, 2025 by kamil-kaczor Loading…
2
Added the logic to fix the warmup phase for spec decoding when enforce_eager is not used
#880 opened Feb 28, 2025 by pallavijaini0525 Loading…
2
Add possibility to execute with LoRA adapter for lm_eval
#879 opened Feb 28, 2025 by mkrze • Draft
Delayed cherrypick
#877 opened Feb 28, 2025 by kamil-kaczor • Draft
Allow to use flex_attention instead of FSDPA in HPUAttentionImpl
#876 opened Feb 27, 2025 by m-a-nowak • Draft
[Gaudi][Model] Qwen2.5-vl New Model Issue o PR to enable a new model
#870 opened Feb 26, 2025 by malkomes Loading…
1
10
[CI] Add APC tests
#866 opened Feb 25, 2025 by kzawora-intel Loading…
Update Dockerfile.hpu
#864 opened Feb 25, 2025 by michalkuligowski • Draft
Update requirements-hpu.txt for open telemetry tracing support
#857 opened Feb 21, 2025 by louie-tsai Loading…
1
enable multi-modal embedding for TIGER-Lab/VLM2Vec-Full T+I on HPU
#854 opened Feb 20, 2025 by libinta Loading…
1
Port delayed sampling to habana_main
#849 opened Feb 20, 2025 by madamczykhabana • Draft
Draft: Another attempt at v1 HPU integration
#831 opened Feb 14, 2025 by kzawora-intel • Draft
19 of 23 tasks
Extend accuracy tests for models that we support
#824 opened Feb 13, 2025 by AnetaKaczynska Loading…
4
Resolve Speculative Decode RTE
#823 opened Feb 13, 2025 by tannervoas742 Loading…
1
enable LoRA for embedding models
#821 opened Feb 12, 2025 by skaulintel Loading…
2
Update documentation to reflect current bucket defaults
#817 opened Feb 12, 2025 by nngokhale Loading…
1
support inc dynamic quant deepseek
#814 opened Feb 11, 2025 by changwangss • Draft
1
support inc dynamic quantization
#803 opened Feb 8, 2025 by changwangss • Draft
2
Support qwenvl model for HPU New Model Issue o PR to enable a new model
#793 opened Feb 7, 2025 by yingjie-han Loading…
3
[DEEPSEEK_V3/R1] includes features of fp8 dequant, MLA, Expert parallelism
#792 opened Feb 6, 2025 by xuechendi Loading…
1
Enable roberta embedding
#786 opened Feb 5, 2025 by yeonsily Loading…
11
[DO NOT MERGE][PoC] Mark dynamic shapes in torch.compile mode
#755 opened Jan 29, 2025 by kzawora-intel • Draft
1
Pipeline Parallelism implementation.
#731 opened Jan 23, 2025 by jmaksymczuk • Draft
6
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 Loading…
10
ProTip! Mix and match filters to narrow down what you’re looking for.