XiongjieDai GPU-Benchmarks-on-LLM-Inference issues

XiongjieDai / GPU-Benchmarks-on-LLM-Inference

Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?

1.11k stars 43 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Do these benchmarks include the MLX version of Llama?

#20 JordyScript opened 1 week ago
0
Prompt processing in A100 SXM 80GB

#19 charleswg opened 1 month ago
2
any chance of a 70b q8 column for the inference tables?

#18 haydonryan opened 1 month ago
1
Apple Silicon boosted by new macOS "Sequoia" - update required!

#17 bluemoehre closed 1 month ago
2
Horizontal scaling

#16 brutuscat opened 2 months ago
1
Test with amd GPU for comparison (consumer and entreprise GPU)

#15 Blast02 opened 3 months ago
0
Would be Very interesting to see performance of new Ryzen 5 processors.

#14 rbrus opened 3 months ago
1
Any plans to run something bigger such as Deepseek-coder?

#13 adriangalilea opened 3 months ago
0
Anyone care to run it with Intel Arc A770 16 GB?

#12 MLSci opened 5 months ago
0
Which GPU benchmark you would like to see?

#11 XiongjieDai closed 6 months ago
6
Include a version of lab to Llamma 3 for the RTX 3060 (12Gb)

#10 Pablo-Oliveira closed 6 months ago
2
First test run

#9 Pablo-Oliveira closed 7 months ago
3
Question about the testing result of Multiple GPUs

#8 hellfire7707 closed 7 months ago
3
Anyone care to run it with RX 7800xt 16 GB?

#7 maifeeulasad opened 7 months ago
0
Anyone care to run it with RTX 4060 ti 16 GB?

#6 maifeeulasad opened 7 months ago
0
confusion in naming of NVIDIA RTX 6000 ADA

#5 gileneusz closed 7 months ago
5
Request to Add TTFT Metrics to Benchmark Results

#4 rafklu closed 7 months ago
1
Add M3 Max 30C GPU/96G RAM Results

#3 LuvLetter closed 6 months ago
1
Why is A6000 better than ada in table?

#2 Phate334 closed 7 months ago
2
Test data for two additional Macs

#1 MichaelDays closed 7 months ago
1