Skip to content

Pull requests: vllm-project/tpu-inference

New pull request New
61 Open 1,029 Closed
61 Open 1,029 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

Revert vllm weight loading to fix OOM
#1127 opened Nov 19, 2025 by kyuyeunk Loading…
1
Skip size calculation during async copy wait=True
#1126 opened Nov 19, 2025 by rupengliu-meta Loading…
1
[TPU Offload][WIP] Separate offload manager and cpu-cache backend, and code structure refactor
#1122 opened Nov 18, 2025 by juncgu-google Loading…
1
[Bug fix] Fix log probabilities handling
#1114 opened Nov 16, 2025 by wenxindongwork Loading…
2
DP support for GPT OSS
#1096 opened Nov 13, 2025 by wenxindongwork • Draft
1
[Misc] Fix model dtype not being configured correctly
#1093 opened Nov 13, 2025 by kyuyeunk Loading…
1
[Llama4 Guard] Add JAX Llama-Guard-4-12B Text Portion
#1090 opened Nov 13, 2025 by JiriesKaileh Loading…
125
Enable Pipeline Parallelism on Jax models
#1077 opened Nov 12, 2025 by Chenyaaang Loading…
1 of 8 tasks
2
Disable E2E DP test unless nightly
#1061 opened Nov 10, 2025 by wenxindongwork Loading…
2
Exposes graphdef for flax models.
#1059 opened Nov 10, 2025 by wang2yn84 Loading…
2
Enable Pipeline Parallelism on Jax runner
#1053 opened Nov 8, 2025 by Chenyaaang Loading…
1 of 8 tasks
1
[GPT-OSS] inital commit to use MoE kernel
#1045 opened Nov 7, 2025 by bzgoogle • Draft
1
Enable Pipeline Parallelism on jax worker
#1043 opened Nov 7, 2025 by Chenyaaang Loading…
1 of 8 tasks
25
Update v7's jax requirements
#1037 opened Nov 7, 2025 by qihqi Loading…
1
[Docs] fix dead links in multiple documentation pages
#1027 opened Nov 6, 2025 by mattheliu Loading…
3 tasks done
Support float8_e4m3fn dtype weight loading for jax
#1024 opened Nov 6, 2025 by inho9606 Loading…
1
Remove SKIP_JAX_PRECOMPILE
#1018 opened Nov 5, 2025 by kyuyeunk Loading…
1
Support Embedding Model/Task
#1015 opened Nov 5, 2025 by carlesoctav Loading…
1
28
[Misc] Add CODEOWNERS to the project.
#988 opened Oct 31, 2025 by py4 Loading…
8
Update tpu_worker_jax.py
#982 opened Oct 30, 2025 by fenyuan-gg Loading…
[GPT-OSS] add unit test for GPT-OSS
#978 opened Oct 30, 2025 by bzgoogle • Draft
1
[DeepSeek][Do-Not-Merge] experimental PR for DeepSeek optimization
#977 opened Oct 30, 2025 by bzgoogle • Draft
1
[FIX] Add dummy get_input_embeddings to fix vLLM model type check
#971 opened Oct 29, 2025 by kuafou Loading…
1
3
[Spec Decoding] Reduce TPU <-> CPU data transfer
#961 opened Oct 28, 2025 by Lumosis Loading…
1
Update README.md
#956 opened Oct 27, 2025 by bvrockwell Loading…
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.