Skip to content

Pull requests: HabanaAI/vllm-fork

New pull request New
62 Open 842 Closed
62 Open 842 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

Automatic Prefix Caching - fully cached prefill
#982 opened Mar 28, 2025 by adobrzyn • Draft
Fix multi-node for HPU
#981 opened Mar 28, 2025 by afierka-intel • Draft
enable VLLM_MLA_PERFORM_MATRIX_ABSORPTION=0
#980 opened Mar 28, 2025 by yangulei Loading…
add torch profiler for the LLM engine
#979 opened Mar 28, 2025 by yangulei Loading…
remove slicing in static-quant + dynamic-MoE mode
#978 opened Mar 28, 2025 by yangulei Loading…
Deepseek r1 fp8matmul
#977 opened Mar 27, 2025 by xuechendi • Draft
Fix APC on v0 habana Issues or PRs submitted by Habana Labs
#975 opened Mar 27, 2025 by adobrzyn Loading…
6
Enable torchrun on Gaudi
#974 opened Mar 27, 2025 by czhu15 Loading…
2
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…
1
Optimize rope if head_size == rotary_dim
#968 opened Mar 26, 2025 by kdamaszk Loading…
4
Move torch.compile to HPUModelRunnerBase
#966 opened Mar 26, 2025 by anko-intel Loading…
3
[SW-222977] Fix for test_lora_manager_hpu.py
#965 opened Mar 25, 2025 by rsshaik1 Loading…
1
Update linear.py
#964 opened Mar 25, 2025 by michalkuligowski • Draft
6
[SW-223065] Sync commits from habana_main to master_next in vllm-fork
#960 opened Mar 25, 2025 by RonBenMosheHabana Loading…
Re-quantize the Official FP8 Model Using INC
#959 opened Mar 25, 2025 by yiliu30 • Draft
2
Update layers.py
#957 opened Mar 25, 2025 by michalkuligowski • Draft
20
Perform KV cache update on flat layout
#955 opened Mar 25, 2025 by mswiniarsk • Draft
Moved set_indices_and_offsets into prepare_prompt and prepare_decode
#949 opened Mar 24, 2025 by jczaja Loading…
4
Rebase - 2025.03.24
#947 opened Mar 24, 2025 by kzawora-intel Loading…
5
Add get_cache call in cross-attention to support fp8
#946 opened Mar 24, 2025 by jkaniecki • Draft
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…
merged_prefill+ - initial cleanup
#942 opened Mar 21, 2025 by madamczykhabana Loading…
7
add ScaleToHwAligned for loading fp8 vllm model
#941 opened Mar 21, 2025 by changwangss Loading…
1
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.