Skip to content

Pull requests: vllm-project/tpu-inference

New pull request New
61 Open 1,099 Closed
61 Open 1,099 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

Refactor moe codebase ready ONLY add when PR is ready to merge/full CI is needed
#1199 opened Nov 29, 2025 by kyuyeunk Loading…
1
[Bugfix] Fix error when using trust remote code ready ONLY add when PR is ready to merge/full CI is needed
#1198 opened Nov 27, 2025 by kyuyeunk Loading…
1
Update README.md
#1197 opened Nov 27, 2025 by bvrockwell Loading…
1
[CI] Improve the procedure of waiting vllm serve
#1196 opened Nov 27, 2025 by dennisYehCienet Loading…
3
Enable expert parallelism in mxfp4 path
#1195 opened Nov 27, 2025 by kyuyeunk Loading…
1
[Spec][Eagle3] Pass state through jit boundary to prevent long compilation time
#1192 opened Nov 27, 2025 by py4 Loading…
2
Integrate MLA v1 into DeepSeek-v3
#1190 opened Nov 26, 2025 by gpolovets1 Loading…
1
fix(rpa-v3): add sliding window mask to h64 kernel and attention_sink to h128
#1185 opened Nov 26, 2025 by erfanzar Loading…
1
1
Add 1st iteration of pre-merge pipeline
#1175 opened Nov 25, 2025 by jcyang43 • Draft
1
[Qwix/Flax] Upgrade to Flax 0.12.0 + Qwix 0.1.4
#1170 opened Nov 25, 2025 by jrplatin Loading…
2
[do not merge] test status check POC ready ONLY add when PR is ready to merge/full CI is needed
#1168 opened Nov 25, 2025 by khluu Loading…
1
[Feat][WIP][TPU Offload] KV cache offload to local cpu buffer
#1163 opened Nov 24, 2025 by juncgu-google Loading…
3
[MISC] Removed problematic local path for CONFTEST_DIR
#1141 opened Nov 20, 2025 by JiriesKaileh Loading…
3
DP support for GPT OSS
#1096 opened Nov 13, 2025 by wenxindongwork • Draft
1
[Misc] Fix model dtype not being configured correctly ready ONLY add when PR is ready to merge/full CI is needed
#1093 opened Nov 13, 2025 by kyuyeunk Loading…
1
Enable Pipeline Parallelism on Jax models ready ONLY add when PR is ready to merge/full CI is needed
#1077 opened Nov 12, 2025 by Chenyaaang Loading…
1 of 8 tasks
2
Exposes graphdef for flax models.
#1059 opened Nov 10, 2025 by wang2yn84 Loading…
2
Enable Pipeline Parallelism on Jax runner ready ONLY add when PR is ready to merge/full CI is needed
#1053 opened Nov 8, 2025 by Chenyaaang Loading…
1 of 8 tasks
9
[GPT-OSS] inital commit to use MoE kernel
#1045 opened Nov 7, 2025 by bzgoogle • Draft
1
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…
2
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
29
Update tpu_worker_jax.py
#982 opened Oct 30, 2025 by fenyuan-gg Loading…
ProTip! Exclude everything labeled bug with -label:bug.