|
Welcome to vLLM Forums! :wave:
|
|
1
|
2300
|
March 24, 2025
|
|
About the General category
|
|
0
|
183
|
March 17, 2025
|
|
Clef/clef decision model support
|
|
1
|
18
|
November 11, 2026
|
|
Help build the local AI community in vLLM!
|
|
1
|
29
|
November 10, 2026
|
|
Qwen3-Omni Realtime in turn mode: how should old audio history be managed?
|
|
2
|
19
|
November 9, 2026
|
|
Best practices for deploying vLLM with Ray on SLURM-based university HPC clusters?
|
|
1
|
15
|
November 8, 2026
|
|
Does this mean that vLLM does not support multiple RDNA3 gpus?
|
|
3
|
27
|
November 7, 2026
|
|
Handling client-side socket timeouts and stream drops on high-latency mobile endpoints
|
|
1
|
13
|
November 7, 2026
|
|
2 vllm docker on same host
|
|
4
|
561
|
November 5, 2026
|
|
What about the support for MAC
|
|
1
|
42
|
November 2, 2026
|
|
Gemma-4 issue while inference setup
|
|
1
|
39
|
October 30, 2026
|
|
Question about max_num_seqs
|
|
2
|
158
|
October 28, 2026
|
|
Some requests never complete: token generation keeps running but the response never finishes (looks like an infinite generation loop)
|
|
1
|
85
|
October 22, 2026
|
|
vLLM 0.20.1, Radeon AI 9700, 1 CPU core at 100%
|
|
8
|
902
|
October 21, 2026
|
|
/v1/systemone with Cloudflare/clef-flash not working on v0.32.0
|
|
1
|
80
|
October 19, 2026
|
|
Question about --enable-chunked-prefill and --max-num-batched-tokens
|
|
3
|
153
|
November 11, 2026
|
|
Handling request timeouts and KV cache bloat during bursty async workloads in vLLM
|
|
1
|
93
|
October 7, 2026
|
|
Audio_tower module missing
|
|
1
|
66
|
October 5, 2026
|
|
Is provider KV caching sufficient for agent swarms and long run agents?
|
|
2
|
136
|
October 1, 2026
|
|
Methods for Server-Side Parameter Optimization in VLLM Performance Benchmarking
|
|
1
|
113
|
September 29, 2026
|
|
Presentation on context, expert, data and tensor parallelism in vLLM
|
|
1
|
200
|
September 22, 2026
|
|
Add LLM observability data management
|
|
2
|
109
|
September 16, 2026
|
|
Vllm推理指标如何做可视化？
|
|
2
|
370
|
September 16, 2026
|
|
[RFC & PR Stack] Application-Directed Prefix Checkpoints for Hybrid GDN/Mamba (Up to 7.6x Speedup on L40S)
|
|
6
|
172
|
September 15, 2026
|
|
vLLM-0.23.0 lora加载问题
|
|
1
|
117
|
September 15, 2026
|
|
vLLM 0.29 7900xtx or 890m 1 cpu core 100%
|
|
8
|
344
|
September 14, 2026
|
|
Muse glimmer - how to disable thinking
|
|
1
|
290
|
September 11, 2026
|
|
Not able to run amd/Qwen3.8-27B-Quark-AWQ-INT4-W4A16 on rocm
|
|
1
|
148
|
September 9, 2026
|
|
vLLM-Ascend在银河麒麟桌面版上不开Eager就报错，开了性能暴跌，换服务器版就正常，这是系统差异导致的吗？
|
|
1
|
128
|
September 4, 2026
|
|
我用单卡跑通了deepseek-v4-flash-0731的dspark模式
|
|
1
|
281
|
August 22, 2026
|