Skip to content

Pull requests: vllm-project/vllm

New pull request New
Clear current search query, filters, and sorts
457 Open 5,126 Closed
457 Open 5,126 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

[model] AddRelPositionMultiHeadedAttention documentation Improvements or additions to documentation unstale
#4956 opened May 21, 2024 by rajveer43 Loading…
1
3
[Hardware][Intel] fp8 kv cache support for CPU x86 CPU
#5492 opened Jun 13, 2024 by jikunshang • Draft
13
[Frontend] support only use linear lora modules in attention needs-rebase unstale
#5483 opened Jun 13, 2024 by jinzhen-lin Loading…
2
[Usage] Clarify and Update Argument for Specifying Model Revisions frontend needs-rebase unstale
#5453 opened Jun 12, 2024 by Etelis Loading…
1
19
[Bugfix] Take the VRAM usage of prompt_logprobs into account needs-rebase unstale
#5355 opened Jun 8, 2024 by Conless Loading…
5
15
[BugFix]Fix the problem that StopChecker assumes a single token produ… needs-rebase unstale
#5243 opened Jun 4, 2024 by IcyFeather233 Loading…
3
[Misc] Adding Speculative decoding to Throughput Benchmarking script needs-rebase unstale
#5223 opened Jun 3, 2024 by abhibambhaniya Loading…
3
[Bugfix] [Frontend] vLLM api_server.py when using with prompt_token_ids causes error. frontend needs-rebase unstale
#5187 opened Jun 1, 2024 by TikZSZ Loading…
1
2
[Bugfix] Fix illegal memory access for lora
#5169 opened May 31, 2024 by sfc-gh-zhwang • Draft
1
@rkooo567
4
[Core] Bump up the default of --gpu_memory_utilization to be more similar to TensorRT Triton's default documentation Improvements or additions to documentation frontend needs-rebase unstale
#5158 opened May 31, 2024 by alexm-neuralmagic Loading…
20
[KERNEL] int8 quantization kernel refactoring & optimization WIP needs-rebase unstale
#5146 opened May 31, 2024 by ZelboK Loading…
8
[Bugfix] Adds outlines performance improvement
#5053 opened May 26, 2024 by lynkz-matt-psaltis • Draft
4
[WIP] Make chunekd prefill work with lora needs-rebase
#4994 opened May 23, 2024 by rkooo567 Loading…
2
[BugFix] Fix fp8 quantizer unstale
#4593 opened May 4, 2024 by Kev1ntan Loading…
2
[Misc] Support HF Hub remote loading for LoRA adapters documentation Improvements or additions to documentation needs-rebase unstale
#4939 opened May 21, 2024 by Isotr0py Loading…
3 tasks done
1
@Yard1
5
Adding idefics2 needs-rebase unstale
#4937 opened May 21, 2024 by jc9123 Loading…
1
@ywang96
16
[Performance] [Speculative decoding] Support draft model on different tensor-parallel size than target model
#4933 opened May 21, 2024 by GeauxEric • Draft
1
4
[CI/Build] Make marlin kernel build conditional. ci/build needs-rebase
#4905 opened May 19, 2024 by esmeetu Loading…
6
[Build/CI] Extending AMD Tests ci/build needs-rebase unstale
#4875 opened May 17, 2024 by Alexei-V-Ivanov-AMD Loading…
3
Add a new kernel for fusing the dequantization in fused-moe gemm needs-rebase unstale
#4841 opened May 15, 2024 by RezaYazdaniAminabadi Loading…
2
[Misc] Logits processor plugins documentation Improvements or additions to documentation frontend needs-rebase unstale
#4769 opened May 11, 2024 by NadavShmayo Loading…
@rkooo567
10
[Kernel] sliding window support in paged_attention_v1/v2 kernels
#4768 opened May 11, 2024 by mmoskal • Draft
@rkooo567
2
[Misc] Added devcontainer to help vscode dev setup unstale
#4720 opened May 9, 2024 by ElefHead Loading…
1
add TypeLogitsProcessor
#4712 opened May 9, 2024 by eitanturok • Draft
[Draft] [FP8] CUTLASS FP8 matrix multiply
#4662 opened May 7, 2024 by pcmoritz • Draft
1
ProTip! Follow long discussions with comments:>50.