Skip to content

Pull requests: vllm-project/vllm

New pull request New
1,301 Open 16,855 Closed
1,301 Open 16,855 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

FP8 KV cache append optimized with precomputed inverse scale
#31514 opened Dec 30, 2025 by tfpre Loading…
5 tasks
4
[Model] Enable LoRA support for tower and connector in LLaVA documentation Improvements or additions to documentation
#31513 opened Dec 30, 2025 by jayhemnani9910 Loading…
8
[Hardware][Power] Add IBM MASS + NUMA optimizations for POWER8 cpu Related to CPU backends documentation Improvements or additions to documentation
#31512 opened Dec 30, 2025 by Scottcjn Loading…
4 tasks
8
[Core] Deduplicate generate/encode logic in AsyncLLM frontend ready ONLY add when PR is ready to merge/full CI is needed v1
#31510 opened Dec 29, 2025 by njhill Loading…
4
[2/n] Migrate kernels to libtorch stable ABI ci/build cpu Related to CPU backends nvidia
#31509 opened Dec 29, 2025 by mikaylagawarecki • Draft
5 tasks
2
[Minor] Various small code cleanups/simplifications frontend multi-modality Related to multi-modality (#4194) ready ONLY add when PR is ready to merge/full CI is needed structured-output v1
#31508 opened Dec 29, 2025 by njhill Loading…
4
Add embedding input functionality for disabled modalities multi-modality Related to multi-modality (#4194) tpu Related to Google TPUs v1
#31506 opened Dec 29, 2025 by reaganjlee • Draft
5 tasks
4
[Bugfix]Fix pooling model always disabled due to incorrect PP rank check v1
#31505 opened Dec 29, 2025 by vintipandey • Draft
4
[MoE Refactor] Explicit construct mk for flashinfer bf16 kernel
#31504 opened Dec 29, 2025 by zyongye Loading…
9
Migrate meetups & sponsors [2/N] documentation Improvements or additions to documentation
#31500 opened Dec 29, 2025 by esmeetu Loading…
5 tasks
3
[Frontend] add continue_final_message parameter to /embeddings endpoint frontend
#31497 opened Dec 29, 2025 by kevin-pw Loading…
3 of 5 tasks
[CI/Build][Docker] Add centralized version manifest for Docker builds ci/build
#31492 opened Dec 29, 2025 by mritunjaysharma394 Loading…
5 tasks
10
[CI][NIXL] Split DPEP tests ci/build kv-connector ready ONLY add when PR is ready to merge/full CI is needed v1
#31491 opened Dec 29, 2025 by NickLucche Loading…
2
[LoRA] Hide lora_init_id in request.py documentation Improvements or additions to documentation frontend llama Related to Llama models performance Performance-related issues v1
#31489 opened Dec 29, 2025 by jeejeelee • Draft
5 tasks
1
6
[log] enable max_log_len trim only when needed frontend
#31482 opened Dec 29, 2025 by andyxning Loading…
5 tasks
[CI/Build] Add source build test to catch build failures early ci/build
#31481 opened Dec 29, 2025 by mhetrerajat Loading…
5 tasks
4
Optimize Top-K Sigmoid Routing and QKNorm for MiniMax-M2/M2.1 ci/build
#31478 opened Dec 29, 2025 by rogeryoungh Loading…
5 tasks
5
Add docker buildx bake configuration
#31477 opened Dec 29, 2025 by amrmahdi Loading…
7
FlashInferUnification nvidia
#31476 opened Dec 29, 2025 by rajanyadav0307 Loading…
5 tasks done
10
[Model] Add HyperCLOVAX-SEED-Think-32B vision-language model support new-model Requests to new models
#31471 opened Dec 29, 2025 by effortprogrammer • Draft
2 of 3 tasks
5
Remove patched_fused_scaled_matmul_reduce_scatter torch is 2.9.1
#31470 opened Dec 29, 2025 by lengrongfu Loading…
5 tasks
1
feat: Add per-layer MLP size support for Qwen pruning documentation Improvements or additions to documentation qwen Related to Qwen models
#31468 opened Dec 29, 2025 by CedricHwong Loading…
4 of 5 tasks
1
11
fixed mypy warnings for files under vllm/v1/attention nvidia rocm Related to AMD ROCm v1
#31465 opened Dec 29, 2025 by MrIceCreamMan Loading…
3 of 5 tasks
@yewentao256
13
[Bugfix] Apply RMSNorm weight correction for Gemma2 GGUF models
#31464 opened Dec 29, 2025 by kitaekatt • Draft
Add Cogagent Model to vllm documentation Improvements or additions to documentation new-model Requests to new models v1
#31463 opened Dec 29, 2025 by JBurtn • Draft
1 of 5 tasks
10
ProTip! Follow long discussions with comments:>50.