Skip to content

Pull requests: HabanaAI/vllm-fork

New pull request New
32 Open 440 Closed
32 Open 440 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

[HPU] Add mark_step configurable for the decoder layer.
#525 opened Nov 20, 2024 by jiminha Loading…
4
[CI/BUILD] Spec decode ci
#524 opened Nov 19, 2024 by xuechendi Loading…
[BUG FIX] [SPEC DECODE] 0.6.4 rebase cause incorrectness in spec decode, fix in this PR
#523 opened Nov 19, 2024 by xuechendi Loading…
1
Update ray_hpu_executor.py
#522 opened Nov 19, 2024 by michalkuligowski Loading…
Clean-up LoRA flow
#518 opened Nov 18, 2024 by SanjuCSudhakaran • Draft
Enable DeepseekV2 Lite/Chat models
#516 opened Nov 18, 2024 by hlin99 Loading…
Add mark_step for baichuan
#515 opened Nov 17, 2024 by YuJiankang Loading…
1
1.19 documentation update
#507 opened Nov 15, 2024 by kzawora-intel • Draft
Random sampler warmup
#506 opened Nov 15, 2024 by mfylcek Loading…
1
Resolved ALIBI bias regression due to porting flat PA
#503 opened Nov 15, 2024 by tannervoas742 Loading…
HPU Specific benchmarks of vLLM
#499 opened Nov 14, 2024 by nageshdn Loading…
3
Support mllama (llama 3.2) model for HPU
#491 opened Nov 13, 2024 by yisonzhu Loading…
4
update vllm_hpu_extension commit to 24039a3
#490 opened Nov 13, 2024 by ccrhx4 Loading…
5
Intern2 habana
#489 opened Nov 13, 2024 by skirdey-inflection Loading…
[WIP] Add HPU support to vLLM v1
#487 opened Nov 12, 2024 by kzawora-intel • Draft
13 of 18 tasks
1
GPTQ Support [Cont.]
#481 opened Nov 8, 2024 by maktukmak Loading…
1
Overhaul padding aware scheduling
#479 opened Nov 8, 2024 by kzawora-intel Loading…
1
enable acc for benchmark_throughput
#472 opened Nov 6, 2024 by hsubramony Loading…
2
[DO NOT MERGE] Upstream codebase diff habana Issues or PRs submitted by Habana Labs
#470 opened Nov 6, 2024 by kzawora-intel • Draft
3
AWQ Support
#458 opened Nov 4, 2024 by maktukmak Loading…
7
to make repetition penalty faster
#442 opened Oct 29, 2024 by ccrhx4 Loading…
11
Add models-tiny CI step with Llama3.2-1B habana Issues or PRs submitted by Habana Labs
#440 opened Oct 28, 2024 by kzawora-intel • Draft
Add HPU information to collect_env script habana Issues or PRs submitted by Habana Labs
#430 opened Oct 25, 2024 by michalkuligowski Loading…
1
GPTQ Support
#421 opened Oct 23, 2024 by maktukmak Loading…
25
[PoC] Add max padding ratio to padding aware scheduler habana Issues or PRs submitted by Habana Labs
#407 opened Oct 18, 2024 by kzawora-intel • Draft
ProTip! Mix and match filters to narrow down what you’re looking for.