Skip to content

Pull requests: vllm-project/vllm

New pull request New
465 Open 5,346 Closed
465 Open 5,346 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[Docs] Update spec decode + structured output in compat matrix documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed
#12373 opened Jan 23, 2025 by russellb Loading…
1
[V1] Increase default batch size for H100/H200 ready ONLY add when PR is ready to merge/full CI is needed
#12369 opened Jan 23, 2025 by WoosukKwon Loading…
3
[Core] add and implement VLLM_LOGITS_PROCESSOR_THREADS
#12368 opened Jan 23, 2025 by akeshet Loading…
3
Update compressed-tensors version ci/build ready ONLY add when PR is ready to merge/full CI is needed
#12367 opened Jan 23, 2025 by dsikka Loading…
2
Set weights_only=True when using torch.load() ready ONLY add when PR is ready to merge/full CI is needed
#12366 opened Jan 23, 2025 by russellb Loading…
2
[Hardware][Intel-Gaudi] Enable FusedSDPA support for Intel Gaudi (HPU)
#12359 opened Jan 23, 2025 by SanjuCSudhakaran • Draft
1
[Misc] Enable proxy support in benchmark script
#12356 opened Jan 23, 2025 by jsato8094 Loading…
1
[Misc] Add FA2 support to ViT MHA layer
#12355 opened Jan 23, 2025 by Isotr0py Loading…
1
[Bugfix] Path join when building local path for S3 clone ready ONLY add when PR is ready to merge/full CI is needed
#12353 opened Jan 23, 2025 by omer-dayan Loading…
1
3
[ROCm] Faster Custom Paged Attention kernels ci/build rocm
#12348 opened Jan 23, 2025 by tjtanaa • Draft
2
[Bugfix] handle alignment of arguments in convert_sparse_cross_attention_mask_to_dense
#12347 opened Jan 23, 2025 by tjohnson31415 Loading…
@heheda12345
5
Flops
#12341 opened Jan 23, 2025 by dianastea • Draft
1
[Build] Only build 9.0a for scaled_mm and sparse kernels ci/build
#12339 opened Jan 23, 2025 by LucasWilkinson Loading…
1
[Frontend] Generate valid tool call IDs when using tokenizer-mode=mistral frontend
#12332 opened Jan 22, 2025 by rafvasq • Draft
5
[Core] Optimizing cross-attention QKVParallelLinear computation
#12325 opened Jan 22, 2025 by NickLucche Loading…
2 tasks
1
[Hardware][Gaudi][Bugfix] Fix error for guided decoding
#12317 opened Jan 22, 2025 by zhouyu5 Loading…
4
[do-not-merge][perf-benchmark] cleanup unused docker images/containers ci/build perf-benchmarks
#12306 opened Jan 22, 2025 by khluu Loading…
1
[Feature][Spec Decode] Simplify the use of Eagle Spec Decode
#12304 opened Jan 22, 2025 by ShangmingCai Loading…
@LiuXiaoxuanPKU
3
[Hardware][Gaudi][Feature] Enable Dynamic MoE for Mixtral
#12303 opened Jan 22, 2025 by zhenwei-intel Loading…
1
[Core] Make disaggregated prefill compatible with pipeline parallelism
#12301 opened Jan 22, 2025 by YuhanLiu11 Loading…
1
[V1][Frontend] Coalesce bunched RequestOutputs frontend performance Performance-related issues ready ONLY add when PR is ready to merge/full CI is needed
#12298 opened Jan 22, 2025 by njhill Loading…
11
[Kernel] Pipe attn_logits_soft_cap through paged attention TPU kernels ci/build
#12294 opened Jan 22, 2025 by fenghuizhang Loading…
5
[Core] tokens in queue metric
#12286 opened Jan 21, 2025 by annapendleton Loading…
4
[Core] Prefill Only Tokens Without KV Cache in Batch Requests (Disagg Prefill)
#12285 opened Jan 21, 2025 by Shaoting-Feng Loading…
1
[CI/Build] Add label automation for structured-output / speculative-decoding ci/build
#12280 opened Jan 21, 2025 by russellb Loading…
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.