Skip to content

Pull requests: vllm-project/vllm

New pull request New
Clear current search query, filters, and sorts
425 Open 4,739 Closed
425 Open 4,739 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][Core] Output sampling: heuristic to choose between candidates needs-rebase unstale
#6589 opened Jul 19, 2024 by NihalPotdar Loading…
11
[ Do Not Merge ] pyzmq based openai server prototypes (w/ protobuf)
#6880 opened Jul 29, 2024 by robertgshaw2-neuralmagic • Draft
1
[ DO NOT MERGE] pyzmq based openai server prototypes (w/ python pickle)
#6874 opened Jul 28, 2024 by robertgshaw2-neuralmagic • Draft
1
Add required libcuda.so ci/build needs-rebase ready ONLY add when PR is ready to merge/full CI is needed
#6864 opened Jul 27, 2024 by sdake Loading…
12
[Model] Teleflm Support
#6822 opened Jul 26, 2024 by horizon94 Loading…
2
[CI/Build] upgrade Dockerfile to ubuntu 22.04
#6820 opened Jul 26, 2024 by samos123 • Draft
1
8
Prefetch all needs-rebase
#6817 opened Jul 26, 2024 by gnpinkert Loading…
2
[Core] Get KV from Block, add KV to Block
#6808 opened Jul 26, 2024 by KrishnaM251 • Draft
2
Update logits processor with tensor caching
#6715 opened Jul 24, 2024 by lynkz-matt-psaltis • Draft
4
[Draft] [Speculative decoding] Use SPMD worker to reduce control plane communication
#6664 opened Jul 23, 2024 by cadedaniel • Draft
1
[DOC] Correct warning about performance
#6654 opened Jul 22, 2024 by casper-hansen Loading…
1
13
[ CI ] Awq Marlin Integration Tests ci/build needs-rebase ready ONLY add when PR is ready to merge/full CI is needed
#6627 opened Jul 22, 2024 by robertgshaw2-neuralmagic Loading…
4
[WIP] Fp8 marlin grouped
#6608 opened Jul 20, 2024 by mgoin • Draft
1
[Kernel] Unify the kernel used in flash attention backend needs-rebase ready ONLY add when PR is ready to merge/full CI is needed
#6052 opened Jul 2, 2024 by LiuXiaoxuanPKU Loading…
28
[Not for review] Pp adag proto
#6526 opened Jul 17, 2024 by ruisearch42 • Draft
1
[Model] Add Support for GPTQ Fused MOE
#6502 opened Jul 17, 2024 by izhuhaoran Loading…
14
[Not for review] Spmd tp rebase ready ONLY add when PR is ready to merge/full CI is needed
#6483 opened Jul 16, 2024 by ruisearch42 • Draft
2
[Not for review] PP ADAG
#6448 opened Jul 15, 2024 by ruisearch42 • Draft
1
[Draft] proposal for ipex quant support
#6440 opened Jul 15, 2024 by jikunshang • Draft
4
torch.compile based model optimizer
#6377 opened Jul 12, 2024 by bnellnm • Draft
8
[ Misc ] Support Act Order in Compressed Tensors needs-rebase ready ONLY add when PR is ready to merge/full CI is needed
#6358 opened Jul 12, 2024 by robertgshaw2-neuralmagic Loading…
25
[BigFix] Fix the lm_head in gpt_bigcode in lora mode
#6357 opened Jul 12, 2024 by maxdebayser Loading…
19
[Model] Implement DualChunkAttention for Qwen2 Models needs-rebase
#6139 opened Jul 4, 2024 by hzhwcmhf Loading…
23
[WIP] Emulated fp8 inference
#6111 opened Jul 3, 2024 by mgoin • Draft
1
[Not for review] Accelerated dag p2p 2
#6075 opened Jul 2, 2024 by ruisearch42 • Draft
ProTip! Updated in the last three days: updated:>2025-01-09.