Skip to content

Pull requests: vllm-project/tpu-inference

New pull request New
75 Open 1,186 Closed
75 Open 1,186 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 tuning for RPA HD64 kernel tuning to improve RPA kernel throughput
#1308 opened Dec 14, 2025 by helloworld1 Loading…
[WIP] [Torchax] fp8 quantization skeleton
#1307 opened Dec 14, 2025 by xingliu14 Loading…
Allow pytest to correctly discover all tests
#1303 opened Dec 12, 2025 by wdhongtw Loading…
Add Quantized Weights Support for MoE Layers ready ONLY add when PR is ready to merge/full CI is needed
#1300 opened Dec 12, 2025 by kyuyeunk Loading…
5
[do not merge ]Get all change files instead of last commit when bootstrap. ready ONLY add when PR is ready to merge/full CI is needed
#1299 opened Dec 12, 2025 by QiliangCui Loading…
1
[test do not review] ready ONLY add when PR is ready to merge/full CI is needed
#1298 opened Dec 12, 2025 by QiliangCui Loading…
1
Add dummy placeholder for unsupported models in the support matrix ready ONLY add when PR is ready to merge/full CI is needed
#1291 opened Dec 12, 2025 by boe20211 Loading…
1
[DRAFT] [DP][Bugfix] Fix bad sharding in non_dp case.
#1288 opened Dec 12, 2025 by py4 Loading…
3
[JAX][MoE] Integrate multiple MoE kernels in MoE modules
#1287 opened Dec 11, 2025 by bzgoogle Loading…
8
[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
docs: update support matrices and improve visuals
#1250 opened Dec 5, 2025 by RobMulla Loading…
Avoid installing CUDA related stuff ready ONLY add when PR is ready to merge/full CI is needed
#1246 opened Dec 4, 2025 by wdhongtw Loading…
6
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
12
[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
ProTip! Updated in the last three days: updated:>2025-12-10.