mlc-ai llm-perf-bench issues

mlc-ai / llm-perf-bench

Apache License 2.0

108 stars 12 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Update Dockerfile.cu121.mlc

#38 wangcx18 opened 3 months ago
0
Llm perf bench for mobile devices

#37 BlindDeveloper opened 5 months ago
0
[BUG] mlc-llm benchmark failed with ROCm

#36 alexhegit opened 6 months ago
0
vllm upgrade to CUDA12

#35 sh1ng opened 8 months ago
0
Update README.md

#34 LeshengJin closed 8 months ago
0
Add Disco performance to README

#33 LeshengJin closed 8 months ago
0
[bug] - crashes when doing build following standard ROCM instructions, related to batching code

#32 Sing-Li closed 8 months ago
12
ERROR: Could not build wheels for flash-attn, which is required to install pyproject.toml-based projects

#31 VincentXWD closed 9 months ago
3
Add standard Apache 2 LICENSE

#30 Sing-Li closed 9 months ago
0
[Llama.cpp] `Q4_0` quantization

#29 LeshengJin closed 9 months ago
0
Update Dockerfile.cu121.mlc

#28 yongjer closed 9 months ago
1
[MultiGPU] Add vLLM Benchmark Docker Script and Instructions

#27 zxybazh closed 9 months ago
0
moving `conda activate` into the container shell

#26 Sing-Li closed 9 months ago
0
Add Dockerfiles for ROCm

#25 junrushao closed 9 months ago
0
Simplify Exllama Docker Build

#24 junrushao closed 9 months ago
0
Update README.md

#23 junrushao closed 9 months ago
0
Update README.md

#22 junrushao closed 9 months ago
0
Update README.md

#21 junrushao closed 9 months ago
0
[MultiGPU] Enable HuggingFace MultiGPU benchmarking

#20 LeshengJin closed 9 months ago
0
add amd rocm instructions

#19 junrushao closed 9 months ago
0
More instructions

#18 junrushao closed 9 months ago
0
Update MLC with latest instructions and numbers

#17 junrushao closed 9 months ago
1
[MultiGPU] Enable Exllama MultiGPU benchmarking

#16 zxybazh closed 9 months ago
0
HF/llama.cpp multi-gpu benchmark

#15 LeshengJin closed 9 months ago
0
Update README.md

#14 junrushao closed 10 months ago
0
can 8gb rtx 3060 run the 13b model?

#13 hiqsociety closed 9 months ago
1
which repo to download from hugging face for 7b / 13b to try out?

#12 hiqsociety closed 9 months ago
1
Docker container seems to be missing Python dependency

#11 JohannesGaessler closed 11 months ago
4
llama.cpp compilation settings are suboptimal

#10 JohannesGaessler closed 11 months ago
7
Perplexity and memory use comparisons would be useful

#9 JohannesGaessler opened 11 months ago
4
llama.cpp thread parameter is suboptimal

#8 JohannesGaessler closed 9 months ago
4
tok/sec metric is not clearly defined

#7 JohannesGaessler closed 11 months ago
1
raise ValueError("Cannot detect local CUDA GPU target!")

#6 AegeanYan closed 11 months ago
6
Enable Docker for Llama.cpp Benchmarking

#5 zxybazh closed 11 months ago
2
Generalize Perf Benchmarking Infra

#4 junrushao closed 11 months ago
0
CUDA error: no kernel image is available for execution on the device

#3 sleepwalker2017 closed 11 months ago
18
Use prebuilt TVM installation in benchmarking

#2 junrushao closed 11 months ago
0
Update README.md

#1 yzh119 closed 11 months ago
0