Skip to content

Pull requests: vllm-project/tpu-inference

New pull request New
42 Open 880 Closed
42 Open 880 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[TPU host offload] delta load optimization for tpu connector local
#941 opened Oct 26, 2025 by saikat-royc Loading…
[Multi-host] Fix bugs in the deployment script
#940 opened Oct 25, 2025 by Lumosis Loading…
1
[do not review yet] Get rid of a2a
#939 opened Oct 24, 2025 by vanbasten23 • Draft
1
Reduce the host overhead for LoRA
#930 opened Oct 23, 2025 by vanbasten23 Loading…
4
[multi-host] add quick start guide
#928 opened Oct 23, 2025 by Lumosis Loading…
1
[Requirements] Bump JAX/JAXLib to 0.8.0
#927 opened Oct 23, 2025 by jrplatin Loading…
1
Fix issues when running multiple LoRA tests on the v6e-8 machine.
#926 opened Oct 23, 2025 by vanbasten23 Loading…
2
[Feature] Code implementation of Async Scheduler
#924 opened Oct 23, 2025 by cychiuak Loading…
4
[Spec Decoding] Merge jitted helpers for eagle3
#920 opened Oct 22, 2025 by Lumosis Loading…
31
[Kernel] Refactor ragged_paged_attention to proxy for default and hd64
#918 opened Oct 22, 2025 by yaochengji • Draft
1
[Requirements] Bump TPU Info to 0.6.0
#917 opened Oct 22, 2025 by jrplatin Loading…
2
PP for single host
#914 opened Oct 21, 2025 by Chenyaaang • Draft
[Draft] Skip build if only docs/icons changed
#908 opened Oct 21, 2025 by boe20211 • Draft
1
[WIP] Add Qwen3-Omni model
#896 opened Oct 19, 2025 by eitanporat Loading…
add jax support for Qwen2VL
#893 opened Oct 18, 2025 by shungcp Loading…
[Doc] Docker guide extended
#890 opened Oct 17, 2025 by hosseinsarshar Loading…
Data Parallelism support
#865 opened Oct 14, 2025 by wenxindongwork • Draft
21
[GPT-OSS] JAX implementation of GPT-OSS
#861 opened Oct 14, 2025 by bzgoogle Loading…
14
[CI] remove lora_bias_stacked as it is deprecated in vllm
#835 opened Oct 11, 2025 by bzgoogle Loading…
3
lora spmd
#802 opened Oct 8, 2025 by vanbasten23 • Draft
feat: Add a procedures to record the vllm and tpu_inference's commit hashes in CI pipeline (WIP)
#795 opened Oct 7, 2025 by dennisYehCienet Loading…
1
update max_model_len to plus 1 to adjust vllm change
#793 opened Oct 6, 2025 by Chenyaaang • Draft
1
Prototyping load weight scale for qwen3.
#741 opened Sep 25, 2025 by inho9606 Loading…
[Test only] Remove the model cache
#725 opened Sep 22, 2025 by QiliangCui Loading…
[kernel][RPA v3] Use dummy DMA on wait to save SREGs usage
#718 opened Sep 19, 2025 by lsy323 • Draft
1
ProTip! Updated in the last three days: updated:>2025-10-24.