Pinokio
Feed
Apps
Remote
Create
App
github-com-vllm-project-vllm
x
Search
Download Pinokio
Switch to dark mode
Sign in
Create account
Join
Switch to dark mode
Sign in
Create account
Join
vllm
Share
github.com/vllm-project/vllm
Updated 9mo ago
A high-throughput and memory-efficient inference and serving engine for LLMs
Follow
0
Loading community details…
Loading project owner…
Loading launchers…
Check-ins
Feed
Dev
Loading check-ins…
Community
Search this app
Sort by
Recent activity
Newest
Top: Past day
Top: Past week
Top: Past month
Top: Past year
Top: All
Create post
Ask or share about vllm…
Loading...
Feed
Apps
Create
Remote
0
Projects using this repository
No references listed yet.
Check-ins
(0)
Recent commits
Vllm CPU benchmark suite improvement (#34128)
Louie Tsai
9 months ago
55a1a95
[Bug Fix] Fix `naive_block_assignment` always defaulting to False due to arg misalignment (#33848)
Runkai Tao
9 months ago
e1d97c3
[Bugfix] Fix MTP accuracy for GLM-5 (#34385)
Michael Goin
9 months ago
ec12d39
Fix Mistral config remap to accept compressed-tensors quantization #34028 (#34104)
baonudesifeizhai
9 months ago
f589761
[bugfix] refactor FunASR's _get_data_parser (#34397)
AllenDou
9 months ago
386bfe5
[BugFix] Fix DP chunking (#34379)
Lucas Wilkinson
9 months ago
136b0bf
[Bugfix] Fix Sparse24 Compressed Tensors models (#33446)
Kyle Sayers
9 months ago
e9cd691
Fix DeepSeek-OCR tensor validation for all size variants (#34085)
Yichuan Wang
9 months ago
80f2ba6
[Refactor] Pass Renderer to Input Processor (#34329)
Cyrus Leung
9 months ago
b96f731
[Refactor] Move validation to params definitions (#34362)
Cyrus Leung
9 months ago
ced2a92