|
About the Hardware Support category
|
|
0
|
160
|
March 20, 2025
|
|
Can Qwen 3.5 models (397B or 9B) run on a single TPU v5e-8 node?
|
|
3
|
29
|
August 15, 2026
|
|
ROCm/vLLM issues compared to CUDA/vLLM
|
|
3
|
91
|
August 11, 2026
|
|
Support for Nvidia A2 Tensor Core GPU, stuck on shm_broadcast, unsure how to debug
|
|
2
|
111
|
August 6, 2026
|
|
Issue when running vllm on the cpu
|
|
1
|
70
|
August 4, 2026
|
|
Performance Tuning for L40s with Qwen36-35B
|
|
1
|
112
|
July 29, 2026
|
|
Running vLLM on Intel Arc iGPU
|
|
1
|
163
|
July 26, 2026
|
|
Vllm-ascend会不会支持gemma4多模态功能
|
|
1
|
68
|
July 24, 2026
|
|
INTEL XPU: Dual Arc B60Pro -> Single Arc B70Pro
|
|
1
|
133
|
July 11, 2026
|
|
Making best use of varying GPU generations
|
|
4
|
1241
|
July 4, 2026
|
|
Win11 wsl2 在 AMD RYZEN AI MAX+ 395
|
|
1
|
129
|
July 3, 2026
|
|
Vllm-ascend怎么支持responses
|
|
1
|
147
|
May 27, 2026
|
|
VGPU on podman "No CUDA GPUs are available"
|
|
0
|
64
|
May 23, 2026
|
|
最新开源的Qwen3.6的moe模型，vllm-ascend支持吗？
|
|
1
|
389
|
April 17, 2026
|
|
vLLM hangs during worker initialization on Blackwell PCIe GPUs unless --disable-custom-all-reduce is used
|
|
1
|
1340
|
April 11, 2026
|
|
# SM120 (RTX PRO 6000) NVFP4 MoE Performance Report -- Qwen3.5-397B
|
|
1
|
1641
|
April 11, 2026
|
|
Vllm启动时，日志卡在nccl相关部分，不继续往下
|
|
16
|
1970
|
April 8, 2026
|
|
SM120 (RTX PRO 4000): 6.5x throughput gain and v0.18.1 regression findings
|
|
1
|
1273
|
April 3, 2026
|
|
Mixed GPU support?
|
|
1
|
875
|
March 31, 2026
|
|
MoE config on GH200
|
|
9
|
740
|
February 4, 2026
|
|
Running NVFP4 Nemotron model on Win11/WSL RTX 5080 + 5070 Ti
|
|
2
|
1317
|
February 2, 2026
|
|
Vllm-ascend跑量化qwen2.5_7b问题
|
|
1
|
158
|
February 2, 2026
|
|
vLLM on RTX5090: Working GPU setup with torch 2.9.0 cu128
|
|
18
|
7486
|
January 13, 2026
|
|
Support for RTX 6000 Blackwell 96GB card
|
|
5
|
8583
|
January 5, 2026
|
|
关于vllm-ascend的性能采集的问题
|
|
1
|
172
|
January 5, 2026
|
|
How to apply FA4 on B200?
|
|
3
|
745
|
December 18, 2025
|
|
Npu 310p3 的生成速率
|
|
3
|
433
|
December 2, 2025
|
|
RTX PRO 6000 users seek help, LLAMA 4 NVFP4
|
|
1
|
360
|
November 25, 2025
|
|
Do we support NPU 310
|
|
3
|
345
|
November 21, 2025
|
|
Mindspeed训练完成后的模型部署问题
|
|
8
|
466
|
November 20, 2025
|