Wayne Gao

build error on ubuntu 24.04 after following the build guide

2

**Describe the bug** A clear and concise description of what the bug is. it is build error **To Reproduce** Steps to reproduce the behavior: following the guide to make libnvm...

I following V1 steps from readme, here is the error ``` (LongBench) root@salab-hpedl380g11-03:~/wayne/kvcache/LongBench/LongBench# CUDA_VISIBLE_DEVICES=0 python pred.py --model chatglm3-6b-32k README.md: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 16.0k/16.0k [00:00

[bugs and help need] I followed main readme page guideline, there is connection error and model running error

4

I looks like start vLLM server well ``` (LongBench) root@salab-hpedl380g11-03:~/wayne/kvcache/LongBench# vllm serve THUDM/glm-4-9b-chat --api-key token-abc123 --tensor-parallel-size 4 --gpu-memory-utilization 0.95 --max_model_len 128000 --trust-remote-code INFO 04-26 11:42:40 [__init__.py:239] Automatically detected platform cuda....

[build issue] cuda12.8 torch 2.7 compatiable issue

1

hello expert, could you pleaes help check what is the compatible problem below? I get 0.4.6 tag and I install from flashinfer latest source, my cuda is 12.8, torch is...

failed to bring it up because panic error

1

this is my yml file ``` # permissions and limitations under the License. server: port: 6007 mode: dev static_resource: enable: true relative_path: /portal root_path: ./dist prefix: api: /api/cubefs mysql: host:...

**Describe the bug** A clear and concise description of what the bug is. build error, missing key files to leverage RocksCacheLibWrapper **To Reproduce** Steps to reproduce the behavior: 1. build...

[Feature]: a benchmark tool that figure out how to improve fuse with golang

4

### Contact Details [email protected] ### Is there an existing issue for this? - [x] I have searched all the existing issues ### Is your feature request related to a problem?...

[Bug]: performance tuning help need

16

### Contact Details [email protected] ### Is there an existing issue for this? - [x] I have searched all the existing issues ### Priority low (Default) ### Environment ```markdown - CubeFS...

**Please acknowledge the following before creating a ticket** - [Yes] I have read the GitHub issues section of [REPORTING-BUGS](../blob/master/REPORTING-BUGS). **Description of the bug:** why passthrough does not support polled IO....

[perf tuning discussion] params.sq_thread_idle will impact performance a lot

2

hello expert, this is related with https://github.com/axboe/liburing/issues/1415, after a lot of parameter tuning. I can reach 1300MB/s now. still have gap with fio. but I found one interesting thing is...