|
Welcome to vLLM Forums! :wave:
|
|
3
|
925
|
November 12, 2025
|
|
About the General category
|
|
0
|
55
|
March 17, 2025
|
|
Why is there no effect after changing chat template file?
|
|
4
|
10
|
November 14, 2025
|
|
求救各位大佬看看是什么问题。cuda12.9，pytorch2.8，vllm0.11.0
|
|
3
|
14
|
November 14, 2025
|
|
No throughput improvement for Quantized Qwen-2.5-7B-Instruct?
|
|
4
|
12
|
November 13, 2025
|
|
Native FP8 WMMA Support for AMD RDNA4 (RX 9070 XT / R9700) in vLLM
|
|
1
|
17
|
November 13, 2025
|
|
在V100显卡上，vLLM并发问题
|
|
2
|
22
|
November 13, 2025
|
|
PD分离，D端也会做prefill?
|
|
3
|
20
|
November 13, 2025
|
|
为什么我安装了vllm0.10.2cu130http没有启动
|
|
2
|
24
|
November 12, 2025
|
|
Enable Expert Offloading
|
|
3
|
41
|
November 11, 2025
|
|
How to preserve custom ops when enabling cuda graph?
|
|
1
|
9
|
November 11, 2025
|
|
V0.11.0 CPU Image Missing from Amazon ECR Public Gallery (vllm-cpu-release-repo)
|
|
1
|
11
|
November 11, 2025
|
|
求救，vllm怎么安装cuda13.0
|
|
3
|
40
|
November 11, 2025
|
|
CPU utilization is extremely high during inference and becomes the primary performance bottleneck
|
|
1
|
36
|
November 10, 2025
|
|
How to monkey patch vLLM correctly?
|
|
1
|
20
|
November 8, 2025
|
|
How to give video input to Qwen-3VL with online serving
|
|
2
|
83
|
November 5, 2025
|
|
V1 GPU not free gpu memory
|
|
2
|
21
|
November 5, 2025
|
|
V1 can only handle a very limited number of requests
|
|
1
|
17
|
November 5, 2025
|
|
When running the benchmark with vllm 0.10.1 V1, the GPU usage was very high
|
|
1
|
22
|
November 5, 2025
|
|
Vllm 0.10.1 v1 benchmark stuck
|
|
1
|
35
|
November 5, 2025
|
|
NCCL error across 2 machines 2x4GPUs need advice
|
|
2
|
52
|
November 12, 2025
|
|
Updated rocm/vllm latest and not anymore working
|
|
1
|
34
|
November 4, 2025
|
|
Vllm 0.10.1 v1 benchmark Only a part of the requests can be processed before it gets stuck
|
|
1
|
28
|
November 4, 2025
|
|
Benchmark error
|
|
1
|
13
|
November 4, 2025
|
|
VLLM and Tensor RT
|
|
3
|
17
|
November 4, 2025
|
|
Cachetools Version
|
|
3
|
15
|
November 4, 2025
|
|
New VLLM Release
|
|
1
|
71
|
November 3, 2025
|
|
Anyone knows that can I run Alibaba Wan2.2 Model in Mac M3/M4/M5?
|
|
2
|
28
|
November 3, 2025
|
|
Need help running VLLM on macOS
|
|
3
|
30
|
November 2, 2025
|
|
vLLM install for 5090
|
|
2
|
1684
|
October 31, 2025
|