Skip to content

Pull requests: HabanaAI/vllm-fork

New pull request New
50 Open 818 Closed
50 Open 818 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

Update requirements-hpu.txt
#945 opened Mar 21, 2025 by michalkuligowski Loading…
APC fully cached prefill moved to decode
#944 opened Mar 21, 2025 by adobrzyn • Draft
Update hpu_worker.py
#943 opened Mar 21, 2025 by michalkuligowski Loading…
[WIP] merged_prefill+ - initial cleanup
#942 opened Mar 21, 2025 by madamczykhabana • Draft
add ScaleToHwAligned for loading fp8 vllm model
#941 opened Mar 21, 2025 by changwangss Loading…
Cherry-pick Softmax skip option for greedy
#939 opened Mar 20, 2025 by attafosu • Draft
Enable Delayed Sampling by default
#937 opened Mar 20, 2025 by mswiniarsk Loading…
[PD+DP][WIP]add mooncake store to support xPyD
#936 opened Mar 20, 2025 by jikunshang • Draft
Add VLLM_T_COMPILE_FULLGRAPH flag
#932 opened Mar 19, 2025 by anko-intel Loading…
4
[SW-218309] Updated Tests Workflow To Support Forked PR's
#930 opened Mar 19, 2025 by RonBenMosheHabana Loading…
3
multi-image support for llama3.2 [1/N]
#926 opened Mar 18, 2025 by zhouyu5 Loading…
1
fix server crash when the client use random seed sampling
#924 opened Mar 18, 2025 by yangulei Loading…
1
Enable embedding online serving benchmark test
#922 opened Mar 17, 2025 by yeonsily Loading…
2
Make lazy mode autodetection more robust
#921 opened Mar 17, 2025 by kzawora-intel Loading…
3
fix G2D FP32 gemm. cherry-pick 970ef08dbf
#917 opened Mar 16, 2025 by jikunshang • Draft
3
Fixing (1) tensor size mismatch and (2) missing prepare_cos_sin issues for Phi-3.5
#916 opened Mar 14, 2025 by mrezavand Loading…
3
Split qkv and gate_up for llama; TP overlap with mlp
#915 opened Mar 14, 2025 by tianmu-li Loading…
7
Enable split qkv for LLama and GPTBigCode
#914 opened Mar 14, 2025 by kdamaszk Loading…
4
[Draft] [DNM]PD distributed support for deepseek r1
#912 opened Mar 14, 2025 by jikunshang • Draft
1
Fix spec decoding warmup
#906 opened Mar 11, 2025 by yangw1234 Loading…
3
Synchronize vLLM flags to support cross-node inference
#897 opened Mar 7, 2025 by IT-Forrest Loading…
3
Add LoRA parameter to test_lm_eval_correctness
#894 opened Mar 6, 2025 by mkrze • Draft
1
Cherry-pick of "Selective merged prefill #643"
#893 opened Mar 6, 2025 by kamil-kaczor Loading…
17
Bump jinja2 from 3.1.4 to 3.1.6 dependencies Pull requests that update a dependency file python Pull requests that update python code
#891 opened Mar 6, 2025 by dependabot bot Loading…
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…
3
ProTip! Updated in the last three days: updated:>2025-03-18.