-
-
Notifications
You must be signed in to change notification settings - Fork 16.5k
Pull requests: vllm-project/vllm
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
add ROCM_VERSION_NUM to guard for atomicAdd definitions
rocm
Related to AMD ROCm
#41802
opened May 6, 2026 by
pmaybank
Contributor
Loading…
4 tasks
[Bugfix] DeepSeekV32/v4: respect string='true|false' attribute andunwrap arguments/input wrapper
bug
Something isn't working
deepseek
Related to DeepSeek models
tool-calling
#41801
opened May 6, 2026 by
chaunceyjiang
Collaborator
•
Draft
4 tasks
[Bugfix] Account for truncate_prompt_tokens when computing max_tokens
bug
Something isn't working
frontend
#41800
opened May 6, 2026 by
viktorpusTT
Loading…
3 of 4 tasks
[MM][Gemma4] Respect max_soft_tokens in encoder budget
multi-modality
Related to multi-modality (#4194)
ready
ONLY add when PR is ready to merge/full CI is needed
verified
Run pre-commit for new contributors without triggering other tests
#41799
opened May 6, 2026 by
lesj0610
Contributor
Loading…
3 tasks done
Fix: merge default stop_token_ids with request stop_token_ids in to_sampling_params
frontend
verified
Run pre-commit for new contributors without triggering other tests
#41798
opened May 6, 2026 by
viktorpusTT
Loading…
3 of 4 tasks
[Attention] add triton diff-kv backend for mimo
documentation
Improvements or additions to documentation
v1
#41797
opened May 6, 2026 by
ZJY0516
Member
Loading…
4 tasks
[Docs] Update KV transfer security configuration flags
documentation
Improvements or additions to documentation
#41796
opened May 6, 2026 by
BWAAEEEK
Loading…
[KV Offload] Return None from lookup() for in-flight blocks
ready
ONLY add when PR is ready to merge/full CI is needed
v1
#41795
opened May 6, 2026 by
ronensc
Contributor
Loading…
4 tasks
[Bugfix][CI] Fix Disaggregated test area path
bug
Something isn't working
ci/build
ready
ONLY add when PR is ready to merge/full CI is needed
#41794
opened May 6, 2026 by
NickLucche
Collaborator
Loading…
[KV Offload] Expose SimpleCPU offload metrics
documentation
Improvements or additions to documentation
kv-connector
v1
#41790
opened May 6, 2026 by
OCWC22
Loading…
Fix padded request metadata for Mamba CUDA graphs
nvidia
v1
#41787
opened May 6, 2026 by
tianshu-Michael-yu
Contributor
•
Draft
Upgrade the aiter version to v0.1.13-rc2
ci/build
rocm
Related to AMD ROCm
#41786
opened May 6, 2026 by
wuhuikx
Contributor
Loading…
3 of 6 tasks
[LoRA][Perf] Overlap LoRA weight H2D copies with compute via side CUDA stream
nvidia
#41785
opened May 6, 2026 by
estellaliu233
Loading…
[XPU] Cap topk/topp Triton BLOCK_SIZE to 4096 for deterministic sampling
intel-gpu
Related to Intel GPU
v1
#41783
opened May 6, 2026 by
chaojun-zhang
Contributor
Loading…
4 tasks
Add multimodal embed task-prefix docs and tests
documentation
Improvements or additions to documentation
#41782
opened May 6, 2026 by
maxiaosong1124
Loading…
[Kernel] Fuse logit softcapping into a single Triton kernel
performance
Performance-related issues
#41779
opened May 6, 2026 by
huaxin0
Loading…
[MLA Attention Backend] Add TOKENSPEED_MLA backend for DSR1/Kimi K25 prefill + decode on Blackwell
ci/build
documentation
Improvements or additions to documentation
nvidia
ready
ONLY add when PR is ready to merge/full CI is needed
v1
#41778
opened May 6, 2026 by
zyongye
Member
Loading…
3 of 4 tasks
[Bugfix] Flush final KV block when SimpleCPUOffload request finishes in same step as its last full block
bug
Something isn't working
v1
#41777
opened May 6, 2026 by
JasonKeyiL
Contributor
Loading…
2 tasks
fix: support MIG UUIDs in CUDA_VISIBLE_DEVICES
nvidia
#41776
opened May 6, 2026 by
michaelpersonal
Loading…
[Model Runner V2] FP32 gumbel sampling.
v1
#41775
opened May 6, 2026 by
PatchouliTIS
Contributor
Loading…
4 tasks
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.