Skip to content

Pull requests: vllm-project/vllm

New pull request New
453 Open 5,097 Closed
453 Open 5,097 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

[Bugfix] fused_experts_impl wrong compute type for float32
#11921 opened Jan 10, 2025 by shaochangxu Loading…
1
[Misc] Update benchmark_prefix_caching.py fixed example usage
#11920 opened Jan 10, 2025 by remimin Loading…
1
[Doc] links Tensorizer example documentation Improvements or additions to documentation
#11918 opened Jan 10, 2025 by guspan-tanadi Loading…
6
[Doc] Correct the spelling of GitHub documentation Improvements or additions to documentation
#11915 opened Jan 10, 2025 by Yaminyam Loading…
3
[V1] APC + prompt logprobs unsupported (PR 2/N for v1 sample and prompt logprobs support)
#11910 opened Jan 10, 2025 by afeldman-nm • Draft
1
[FP8][Kernel] Dynamic kv cache scaling factors computation documentation Improvements or additions to documentation
#11906 opened Jan 9, 2025 by gshtras Loading…
1
[Model] Add T5 model (2/2)
#11901 opened Jan 9, 2025 by NickLucche Loading…
2
[Bugfix] Multi-sequence broken
#11898 opened Jan 9, 2025 by andylolu2 Loading…
4
[V1][Core] Autotune encoder cache budget
#11895 opened Jan 9, 2025 by ywang96 Loading…
26
Change clone files mechanism
#11892 opened Jan 9, 2025 by omer-dayan Loading…
1
[Bugfix] support to run partially 2:4 model with CompressedTensors24 scheme
#11889 opened Jan 9, 2025 by jiangjiadi Loading…
1
2
Add device as parameter to TP and rotary_embedding functions
#11888 opened Jan 9, 2025 by chunyuan-w • Draft
1
[optimization] remove python function call for custom activation op ready ONLY add when PR is ready to merge/full CI is needed
#11885 opened Jan 9, 2025 by cennn Loading…
8
add model_glm code
#11883 opened Jan 9, 2025 by zhipuch Loading…
2
[CI] Add auto update workflow for Dockerfile graph ci/build
#11879 opened Jan 9, 2025 by WineChord Loading…
1
2
Updating the high performance vllm docker for AMD Rocm. documentation Improvements or additions to documentation
#11877 opened Jan 9, 2025 by haic0 Loading…
3
[Hardware][Gaudi] Support loading checkpoints quantized using Autofp8
#11869 opened Jan 9, 2025 by zhenwei-intel • Draft
1
[WIP][Kernel] Update cutlass_scaled_mm to support 2d group (blockwise) scaling ci/build
#11868 opened Jan 8, 2025 by LucasWilkinson • Draft
3 tasks
1
[Spec Decode] Add Script for converting HF Eagle checkpoint to vLLM compatible checkpoint documentation Improvements or additions to documentation
#11866 opened Jan 8, 2025 by sroy745 Loading…
6
optimizations
#11860 opened Jan 8, 2025 by kgoyal98 Loading…
1
[CI/Build] Add markdown linter ci/build documentation Improvements or additions to documentation
#11857 opened Jan 8, 2025 by rafvasq Loading…
6
[Bugfix] Fix start_idx for computing slot mapping to avoid uninitiali…
#11851 opened Jan 8, 2025 by ShawnD200 Loading…
3
Implements dual-chunk-flash-attn backend for dual chunk attention with sparse attention support ci/build
#11844 opened Jan 8, 2025 by sighingnow Loading…
2
[Hardware][CPU] Support MOE models on x86 CPU documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed x86 CPU
#11831 opened Jan 8, 2025 by bigPYJ1151 Loading…
7
Add fused_moe config for DeepSeek-V3 ci/build
#11820 opened Jan 7, 2025 by Pernekhan Loading…
2
ProTip! Mix and match filters to narrow down what you’re looking for.