Skip to content

Pull requests: vllm-project/tpu-inference

New pull request New
33 Open 853 Closed
33 Open 853 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

[Chore] Update import path for vllm.utils
#901 opened Oct 20, 2025 by wdhongtw Loading…
[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…
[Feature] [TPU host offload] sglang bench_serving tool example
#892 opened Oct 18, 2025 by saikat-royc Loading…
Added the docker login instructions
#891 opened Oct 17, 2025 by hosseinsarshar 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…
7
[CI] remove lora_bias_stacked as it is deprecated in vllm
#835 opened Oct 11, 2025 by bzgoogle Loading…
3
Enable spmd on lora
#829 opened Oct 10, 2025 by vanbasten23 Loading…
9
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
extract docker build step (wip)
#713 opened Sep 19, 2025 by CienetStingLin Loading…
4
prefill decode microbenchmark for QWen3
#699 opened Sep 16, 2025 by mailvijayasingh Loading…
80
[do nor review/merge] qwen 3 working microbenchmark
#632 opened Sep 3, 2025 by mailvijayasingh Loading…
1
[Draft] Llama4-Guard Support
#626 opened Sep 3, 2025 by JiriesKaileh • Draft
1
[Misc] Upgrade to flax 0.11.2
#603 opened Aug 28, 2025 by py4 Loading…
1
[Draft-WIP- Do Not Merge] RPA Kernel v3 MB for llama
#571 opened Aug 26, 2025 by mailvijayasingh Loading…
Create TorchaxMergedColumnParallelLinearWithLoRA lora wrapper for single chip
#496 opened Aug 18, 2025 by vanbasten23 Loading…
18
Llama4scout logit checking
#475 opened Aug 13, 2025 by gpolovets1 Loading…
Parallelize llama4 implementation weight loading
#457 opened Aug 12, 2025 by KWang1998 Loading…
3
ProTip! no:milestone will show everything without a milestone.