|
About the Hardware Support category
|
|
0
|
189
|
March 20, 2025
|
|
Title: OutOfResources: shared memory (98304 > 65536) on Turing (SM75) — global attention layers with head_dim=512
|
|
2
|
58
|
September 20, 2026
|
|
Is this normal for vllm serve output waiting 1 hour b´before startup
|
|
7
|
161
|
September 9, 2026
|
|
请问一下最新版的vllm-ascend是否支持GLM-5.3 flash
|
|
1
|
278
|
August 28, 2026
|
|
GFX1030 Support PR
|
|
1
|
161
|
August 27, 2026
|
|
Can Qwen 3.5 models (397B or 9B) run on a single TPU v5e-8 node?
|
|
3
|
150
|
August 15, 2026
|
|
ROCm/vLLM issues compared to CUDA/vLLM
|
|
3
|
192
|
August 11, 2026
|
|
Support for Nvidia A2 Tensor Core GPU, stuck on shm_broadcast, unsure how to debug
|
|
2
|
215
|
August 6, 2026
|
|
Issue when running vllm on the cpu
|
|
1
|
133
|
August 4, 2026
|
|
Performance Tuning for L40s with Qwen36-35B
|
|
1
|
225
|
July 29, 2026
|
|
Running vLLM on Intel Arc iGPU
|
|
1
|
373
|
July 26, 2026
|
|
Vllm-ascend会不会支持gemma4多模态功能
|
|
1
|
92
|
July 24, 2026
|
|
INTEL XPU: Dual Arc B60Pro -> Single Arc B70Pro
|
|
1
|
296
|
July 11, 2026
|
|
Making best use of varying GPU generations
|
|
4
|
1321
|
July 4, 2026
|
|
Win11 wsl2 在 AMD RYZEN AI MAX+ 395
|
|
1
|
205
|
July 3, 2026
|
|
Vllm-ascend怎么支持responses
|
|
1
|
219
|
May 27, 2026
|
|
VGPU on podman "No CUDA GPUs are available"
|
|
0
|
86
|
May 23, 2026
|
|
最新开源的Qwen3.6的moe模型，vllm-ascend支持吗？
|
|
1
|
428
|
April 17, 2026
|
|
vLLM hangs during worker initialization on Blackwell PCIe GPUs unless --disable-custom-all-reduce is used
|
|
1
|
1629
|
April 11, 2026
|
|
# SM120 (RTX PRO 6000) NVFP4 MoE Performance Report -- Qwen3.5-397B
|
|
1
|
1958
|
April 11, 2026
|
|
Vllm启动时，日志卡在nccl相关部分，不继续往下
|
|
16
|
2169
|
April 8, 2026
|
|
SM120 (RTX PRO 4000): 6.5x throughput gain and v0.18.1 regression findings
|
|
1
|
1523
|
April 3, 2026
|
|
Mixed GPU support?
|
|
1
|
1153
|
March 31, 2026
|
|
MoE config on GH200
|
|
9
|
837
|
February 4, 2026
|
|
Running NVFP4 Nemotron model on Win11/WSL RTX 5080 + 5070 Ti
|
|
2
|
1528
|
February 2, 2026
|
|
Vllm-ascend跑量化qwen2.5_7b问题
|
|
1
|
183
|
February 2, 2026
|
|
vLLM on RTX5090: Working GPU setup with torch 2.9.0 cu128
|
|
18
|
7913
|
January 13, 2026
|
|
Support for RTX 6000 Blackwell 96GB card
|
|
5
|
9156
|
January 5, 2026
|
|
关于vllm-ascend的性能采集的问题
|
|
1
|
193
|
January 5, 2026
|
|
How to apply FA4 on B200?
|
|
3
|
820
|
December 18, 2025
|