Skip to content

Pull requests: vllm-project/tpu-inference

New pull request New
70 Open 1,169 Closed
70 Open 1,169 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

Support overriding logic for hybrid kv cache padding ready ONLY add when PR is ready to merge/full CI is needed
#1285 opened Dec 11, 2025 by kyuyeunk Loading…
1
[Bugfix][Refactor] Fix compressed tensor moe init ready ONLY add when PR is ready to merge/full CI is needed
#1283 opened Dec 11, 2025 by kyuyeunk Loading…
1
1
[multihost] Integrate expert parallelism to RayExecutor
#1282 opened Dec 10, 2025 by Lumosis Loading…
1
[multihost] Use make_array_from_process_local_data to create global array instead of device_put
#1281 opened Dec 10, 2025 by Lumosis Loading…
4
[Kernel][Misc] Remove jax.named_scope ready ONLY add when PR is ready to merge/full CI is needed
#1278 opened Dec 10, 2025 by kyuyeunk Loading…
1
[do not review][do not submit] ready ONLY add when PR is ready to merge/full CI is needed
#1277 opened Dec 10, 2025 by QiliangCui Loading…
1
Move the If nightly==1 check out of command.
#1276 opened Dec 10, 2025 by QiliangCui Loading…
1
add new kernel and quantization support matrices
#1275 opened Dec 10, 2025 by boe20211 Loading…
1
Fix TPU7x chip counting to account for chiplet architecture
#1266 opened Dec 8, 2025 by burbajr Loading…
7
Add default 'auto' MODEL_IMPL_TYPE that resolves based on architecture ready ONLY add when PR is ready to merge/full CI is needed
#1255 opened Dec 5, 2025 by xingliu14 Loading…
24
docs: update support matrices and improve visuals
#1250 opened Dec 5, 2025 by RobMulla Loading…
Avoid installing CUDA related stuff
#1246 opened Dec 4, 2025 by wdhongtw Loading…
3
update run_in_docker script for running on local env ready ONLY add when PR is ready to merge/full CI is needed
#1243 opened Dec 4, 2025 by ernie-chang Loading…
2
Add workflow to build vLLM-TPU wheel using PyPI tpu-inference ready ONLY add when PR is ready to merge/full CI is needed
#1241 opened Dec 4, 2025 by ylangtsou • Draft
11
[DRAFT] Optimize Dockerfile to reduce image size and build time.
#1226 opened Dec 3, 2025 by py4 Loading…
1
[CI] Fix awq dtype ready ONLY add when PR is ready to merge/full CI is needed
#1220 opened Dec 2, 2025 by kyuyeunk Loading…
1
[Oncall] update the SchedulerConfig interface
#1219 opened Dec 2, 2025 by bzgoogle Loading…
1
Add a SP e2e test.
#1209 opened Dec 2, 2025 by vanbasten23 Loading…
12
Save size in scalar scratch for bo and bq ready ONLY add when PR is ready to merge/full CI is needed
#1201 opened Dec 1, 2025 by rupengliu-meta Loading…
13
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][TPU Offload] KV cache offload to local cpu buffer ready ONLY add when PR is ready to merge/full CI is needed
#1163 opened Nov 24, 2025 by juncgu-google Loading…
11
DP support for GPT OSS
#1096 opened Nov 13, 2025 by wenxindongwork • Draft
1
ProTip! no:milestone will show everything without a milestone.