Skip to content

Pull requests: vllm-project/vllm

New pull request New
406 Open 4,247 Closed
406 Open 4,247 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

Rahul quant merged
#10341 opened Nov 14, 2024 by robertgshaw2-neuralmagic • Draft
2
[Kernel] Add CUTLASS sparse support, heuristics, and torch operators ci/build
#10340 opened Nov 14, 2024 by Faraz9877 Loading…
4
[Perf] Reduce peak memory usage of llama ready ONLY add when PR is ready to merge/full CI is needed
#10339 opened Nov 14, 2024 by andoorve Loading…
2
[bugfix] Fix static asymmetric quantization case ready ONLY add when PR is ready to merge/full CI is needed
#10334 opened Nov 14, 2024 by ProExpertProg Loading…
5
[Tool parsing] Improve / correct mistral tool parsing frontend ready ONLY add when PR is ready to merge/full CI is needed
#10333 opened Nov 14, 2024 by patrickvonplaten Loading…
1
8
[Feature] enable host memory for kv cache
#10330 opened Nov 14, 2024 by YZP17121579 • Draft
2
Rs 24 sparse ci/build needs-rebase
#10329 opened Nov 14, 2024 by robertgshaw2-neuralmagic • Draft
2
[Misc] Add uninitialized params tracking for AutoWeightsLoader
#10327 opened Nov 14, 2024 by Isotr0py • Draft
@DarkLight1337
1
DistServe Prototype
#10321 opened Nov 14, 2024 by Jocn2020 • Draft
1
[Hardware][Cambricon MLU] Add Cambricon MLU inference backend (#9649) ci/build
#10315 opened Nov 14, 2024 by zonghuaxiansheng Loading…
1
[Bugfix] Fix unable to load some models ci/build documentation Improvements or additions to documentation frontend ready ONLY add when PR is ready to merge/full CI is needed release-blocker This PR/issue blocks the next release, therefore deserves highest priority
#10312 opened Nov 14, 2024 by DarkLight1337 Loading…
8
[Model] Support telechat2
#10311 opened Nov 14, 2024 by shunxing12345 Loading…
1
8
[Misc] Change RedundantReshapesPass and FusionPass logging from info to debug ready ONLY add when PR is ready to merge/full CI is needed
#10308 opened Nov 13, 2024 by tlrmchlsmth Loading…
2
[TPU] Implement prefix caching for TPUs ci/build tpu Related to Google TPUs
#10307 opened Nov 13, 2024 by WoosukKwon • Draft
6
[Bugfix] return zero point in static quantization in scaled_int8_quant
#10292 opened Nov 13, 2024 by danieldk Loading…
5
[Model] Add Support for Multimodal Granite Models
#10291 opened Nov 13, 2024 by alex-jw-brooks Loading…
@DarkLight1337
3
[Misc] Update benchmark to support image_url file or http
#10287 opened Nov 13, 2024 by kakao-steve-ai • Draft
1
[Core][Frontend] Add faster-outlines as guided decoding backend ci/build
#10277 opened Nov 13, 2024 by unaidedelf8777 Loading…
5
[torch.compile] PostGradPassManager, Inductor code caching fix, fix_functionalization pass refactor + tests ready ONLY add when PR is ready to merge/full CI is needed
#10273 opened Nov 12, 2024 by ProExpertProg Loading…
13
[Kernel][Hardware][AMD] Add support for GGUF quantization on ROCm ci/build
#10254 opened Nov 12, 2024 by kliuae Loading…
6
[CI/build] update torch to 2.5.1 in publish.yml to match requirements-build.txt ci/build
#10253 opened Nov 12, 2024 by tomeras91 Loading…
2
[misc] Layerwise profile updates
#10242 opened Nov 12, 2024 by varun-sundar-rabindranath Loading…
5
[V1] TPU Prototype ci/build
#10241 opened Nov 12, 2024 by robertgshaw2-neuralmagic • Draft
1
[Hardware] [HPU]add mark_step for hpu Gaudi
#10239 opened Nov 12, 2024 by jikunshang Loading…
5
[Core] Reduce TTFT with concurrent partial prefills frontend ready ONLY add when PR is ready to merge/full CI is needed
#10235 opened Nov 11, 2024 by joerunde Loading…
30
ProTip! What’s not been updated in a month: updated:<2024-10-14.