Skip to content

Issues: vllm-project/vllm

[Roadmap] vLLM Roadmap Q4 2024
#9006 opened Oct 1, 2024 by simon-mo
Open 26
vLLM's V1 Engine Architecture
#8779 opened Sep 24, 2024 by simon-mo
Open 10
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
161 Open 53 Closed
161 Open 53 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
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[Misc] Move some multimodal utils to modality-specific modules needs-rebase ready ONLY add when PR is ready to merge/full CI is needed
#11494 opened Dec 25, 2024 by DarkLight1337 Loading…
2
[Model][LoRA]LoRA support added for MolmoForCausalLM ci/build documentation Improvements or additions to documentation frontend needs-rebase
#11439 opened Dec 23, 2024 by ayylemao Loading…
1
8
fix: add missing bos_token to example templates ci/build needs-rebase
#11432 opened Dec 23, 2024 by toslunar Loading…
11
[Misc] Add image repeat option to benchmark_serving.py (to test hit/miss of MM cache) needs-rebase
#11177 opened Dec 13, 2024 by alexm-neuralmagic Loading…
@alexm-neuralmagic
6
[V1] Supports scheduling asynchronousization on V1 version needs-rebase
#11133 opened Dec 12, 2024 by lixiaolx Loading…
2
[prototype][V1] PP Ray needs-rebase
#11116 opened Dec 11, 2024 by ruisearch42 • Draft
2
[Core] Support offloading KV cache to CPU frontend needs-rebase ready ONLY add when PR is ready to merge/full CI is needed
#10874 opened Dec 3, 2024 by ApostaC Loading…
20
[v1][WIP] Metrics & Stats prototype needs-rebase
#10651 opened Nov 26, 2024 by rickyyx • Draft
16
[V1] VLM prefix caching: Add hashing of images needs-rebase
#10497 opened Nov 20, 2024 by alexm-neuralmagic • Draft
@alexm-neuralmagic
7
Update outlines support to v0.1.4 ci/build needs-rebase
#10490 opened Nov 20, 2024 by Treparme Loading…
1
13
[V1] Replace traversal search with lookup table needs-rebase
#10486 opened Nov 20, 2024 by Abatom Loading…
8
Add support for reporting metrics in completion response headers in o… frontend needs-rebase
#10484 opened Nov 20, 2024 by coolkp Loading…
1
2
Llama32 rocm FA support in upstream needs-rebase
#10461 opened Nov 19, 2024 by maleksan85 • Draft
2
Compressed tensors w8a8 tpu needs-rebase
#10435 opened Nov 18, 2024 by robertgshaw2-neuralmagic • Draft
2
[Core] Interface for accessing model from engine needs-rebase
#10353 opened Nov 15, 2024 by DarkLight1337 Loading…
10
Rahul quant merged ci/build needs-rebase
#10341 opened Nov 14, 2024 by robertgshaw2-neuralmagic • Draft
3
[Kernel] Add CUTLASS sparse support, heuristics, and torch operators ci/build needs-rebase
#10340 opened Nov 14, 2024 by Faraz9877 Loading…
5
[Feature] enable host memory for kv cache needs-rebase
#10330 opened Nov 14, 2024 by YZP17121579 • Draft
4
Rs 24 sparse ci/build needs-rebase
#10329 opened Nov 14, 2024 by robertgshaw2-neuralmagic • Draft
2
DistServe Prototype needs-rebase
#10321 opened Nov 14, 2024 by Jocn2020 • Draft
2
[Core][Frontend] Add faster-outlines as guided decoding backend ci/build needs-rebase
#10277 opened Nov 13, 2024 by unaidedelf8777 Loading…
11
[V1] TPU Prototype ci/build needs-rebase
#10241 opened Nov 12, 2024 by robertgshaw2-neuralmagic • Draft
6 tasks
2
[Frontend][Core] Add Guidance backend for guided decoding ci/build needs-rebase
#10217 opened Nov 11, 2024 by JC1DA Loading…
33
[Not to be submitted] Adding logs for in sd+chunked-prefill needs-rebase
#10186 opened Nov 9, 2024 by sroy745 • Draft
2
[Core][LoRA]Add LoRA for EncoderDecoderModelRunner needs-rebase
#10143 opened Nov 8, 2024 by jeejeelee • Draft
3 tasks
2
ProTip! Exclude everything labeled bug with -label:bug.