Skip to content

Pull requests: vllm-project/vllm

New pull request New
233 Open 1,704 Closed
233 Open 1,704 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

[Frontend] Add prompt token ids into logit processor
#4932 opened May 21, 2024 by xz-liu Loading…
1
[Misc] Minor change to improve FP8 thoughtput by 2%
#4931 opened May 21, 2024 by elfiegg Loading…
2
[Model] add rope_scaling support for qwen2
#4930 opened May 21, 2024 by hzhwcmhf Loading…
1
[Kernel][ROCm][AMD] enable fused topk_softmax kernel for moe layer
#4927 opened May 20, 2024 by divakar-amd Loading…
1
[Docs] Add acknowledgment for sponsors
#4925 opened May 20, 2024 by simon-mo Loading…
1
[Build/CI] Switching to ROCm v. 6.1 in Dockerfile.rocm
#4922 opened May 20, 2024 by Alexei-V-Ivanov-AMD Loading…
[Kernel] Enhance MoE benchmarking & tuning script
#4921 opened May 20, 2024 by WoosukKwon • Draft
@pcmoritz
2
[CI/Build] Make marlin kernel build conditional.
#4905 opened May 19, 2024 by esmeetu Loading…
4
[Bugfix] Fix custom all reduce nvlink check on multi node
#4903 opened May 19, 2024 by esmeetu Loading…
10
Update test_ignore_eos
#4898 opened May 18, 2024 by simon-mo Loading…
3
[Core] Eliminate parallel worker per-step task scheduling overhead
#4894 opened May 18, 2024 by njhill Loading…
@rkooo567
23
[Misc] Load FP8 kv-cache scaling factors from checkpoints
#4893 opened May 17, 2024 by comaniac Loading…
1 task done
7
[Kernel] Correctly invoke prefill & decode kernels for cross-attention (towards eventual encoder/decoder model support)
#4888 opened May 17, 2024 by afeldman-nm • Draft
[Model] Add Phi-2 LoRA support
#4886 opened May 17, 2024 by Isotr0py Loading…
2
@rkooo567
12
[Bugfix] Fix with verifying model max len
#4885 opened May 17, 2024 by dimaioksha Loading…
@rkooo567
7
[Build/CI] Extending AMD Tests
#4875 opened May 17, 2024 by Alexei-V-Ivanov-AMD Loading…
[Draft][CI/Build] Optimize models tests
#4874 opened May 17, 2024 by DarkLight1337 • Draft
@rkooo567
2
[CI/Build] Add health check
#4868 opened May 16, 2024 by pseudotensor Loading…
1
4
Add control panel allow manage multi vllm instances
#4861 opened May 16, 2024 by leiwen83 Loading…
1
10
[Bugfix] Still download from huggingface while set VLLM_USE_MODELSCOPE = true
#4856 opened May 16, 2024 by liuzhenghua Loading…
1
[Bugfix / Core] Prefix Caching Guards (merged with main)
#4846 opened May 16, 2024 by zhuohan123 Loading…
8
[Core] Avoid one broadcast op when propagating metadata
#4844 opened May 16, 2024 by njhill Loading…
4
Add a new kernel for fusing the dequantization in fused-moe gemm
#4841 opened May 15, 2024 by RezaYazdaniAminabadi Loading…
[Core] Cross-attention KV caching and memory-management (towards eventual encoder/decoder model support)
#4837 opened May 15, 2024 by afeldman-nm Loading…
11
[Hardware][Intel] Add LoRA adapter support for CPU backend
x86 CPU
#4830 opened May 15, 2024 by Isotr0py Loading…
1
ProTip! Mix and match filters to narrow down what you’re looking for.