Skip to content

Pull requests: HabanaAI/vllm-fork

New pull request New
43 Open 700 Closed
43 Open 700 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

support inc dynamic quant deepseek
#814 opened Feb 11, 2025 by changwangss Loading…
Fix guided decoding crashes
#811 opened Feb 10, 2025 by kzawora-intel Loading…
5
Rebase 2025-02-10
#810 opened Feb 10, 2025 by kzawora-intel Loading…
support inc dynamic quantization
#803 opened Feb 8, 2025 by changwangss Loading…
Qwen2 vl
#802 opened Feb 7, 2025 by malkomes • Draft
[SW-212072] Extend accuracy tests for models that we support
#800 opened Feb 7, 2025 by AnetaKaczynska Loading…
mszu/merged scheduler
#799 opened Feb 7, 2025 by szutenberg • Draft
[WIP] Updating docs for the vLLM 1.20 release
#798 opened Feb 7, 2025 by PatrykWo Loading…
Pin triton to v3.1.0 for HPU
#796 opened Feb 7, 2025 by iboiko-habana Loading…
Pin triton to v3.1.0 for HPU
#795 opened Feb 7, 2025 by iboiko-habana Loading…
Fix sporadic issue in async_engine/test_api_server tests
#794 opened Feb 7, 2025 by akarnows Loading…
1
Support qwenvl model for HPU
#793 opened Feb 7, 2025 by yingjie-han Loading…
[DEEPSEEK_V3/R1] includes features of fp8 dequant, MLA, Expert parallelism
#792 opened Feb 6, 2025 by xuechendi Loading…
Enable roberta embedding
#786 opened Feb 5, 2025 by yeonsily Loading…
Improve RMSNorm to support 2D inputs
#784 opened Feb 5, 2025 by YangQun1 Loading…
[SW-207299] Recalc scales from user
#774 opened Feb 3, 2025 by linoybu Loading…
4
Fix warmup padding
#759 opened Jan 30, 2025 by mfylcek • Draft
Initial enablement for text-embedding
#758 opened Jan 30, 2025 by libinta Loading…
[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
Allow tests to run in t.compile
#724 opened Jan 22, 2025 by Kacper-Pietkun Loading…
4
[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 Loading…
6
multi-image support for llama3.2
#705 opened Jan 20, 2025 by yma11 Loading…
18
ProTip! What’s not been updated in a month: updated:<2025-01-11.