Skip to content

Pull requests: HabanaAI/vllm-fork

New pull request New
57 Open 894 Closed
57 Open 894 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

Added link for example scripts and FP8 tutorial and documentation
#1032 opened Apr 8, 2025 by MohitIntel Loading…
[deepseek r1] HPU support for deepseek
#1030 opened Apr 8, 2025 by xuechendi Loading…
6
[aice/v1.20.1] PRC branch migration for v1.20.1
#1029 opened Apr 8, 2025 by ranzhejiang Loading…
1
[1.21 cherry-pick] Fix async callback ordering (#1023)
#1028 opened Apr 8, 2025 by madamczykhabana Loading…
[SW-224648] Fix test logs redirection
#1027 opened Apr 8, 2025 by bmyrcha Loading…
[SW-224648] Fix test logs redirection
#1026 opened Apr 8, 2025 by bmyrcha Loading…
Support Data Parallel MOE on HPU
#1022 opened Apr 8, 2025 by xinyu-intel Loading…
[WIP] Bypass detokenize for openai completion
#1021 opened Apr 7, 2025 by tianmu-li • Draft
APC - Remove prompt attn with context and use existing implementation
#1020 opened Apr 7, 2025 by adobrzyn Loading…
2
Michalkuligowski patch update workflows
#1019 opened Apr 7, 2025 by michalkuligowski • Draft
[Deepseek-R1] PR to habana main
#1014 opened Apr 6, 2025 by xuechendi • Draft
18
Enable alibi_slope with FusedSDPA.
#1013 opened Apr 4, 2025 by libinta Loading…
2
Warmup V1
#1012 opened Apr 4, 2025 by iboiko-habana Loading…
Implement Pipeline Parallelism support for HPU.
#1000 opened Apr 2, 2025 by jmaksymczuk Loading…
5
Modify RobertaEmbedding forward as custom op method
#996 opened Apr 1, 2025 by yeonsily Loading…
6
Update gaudi readme about compile mode execution
#993 opened Apr 1, 2025 by afierka-intel • Draft
Remove unnecessary comments and files from deepseek_r1 branch
#991 opened Mar 31, 2025 by kwisniewski98 Loading…
Use the correct fp8 range for G2
#984 opened Mar 31, 2025 by czhu15 Loading…
add torch profiler for the LLM engine
#979 opened Mar 28, 2025 by yangulei Loading…
Enable torchrun on Gaudi
#974 opened Mar 27, 2025 by czhu15 Loading…
3
enable fp32 softmax in flat_pa_mla
#972 opened Mar 27, 2025 by yangulei Loading…
1
workaround cpu fallback when calling max on a bool tensor
#970 opened Mar 26, 2025 by yangw1234 Loading…
3
Update linear.py
#964 opened Mar 25, 2025 by michalkuligowski • Draft
6
Update layers.py
#957 opened Mar 25, 2025 by michalkuligowski • Draft
26
Perform KV cache update on flat layout
#955 opened Mar 25, 2025 by mswiniarsk • Draft
ProTip! Add no:assignee to see everything that’s not assigned.