Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

1Cat-vLLM outpaces Strata on most Tesla V100 tests

AI summary

A community benchmark on four 16 GB Tesla V100 GPUs found that 1Cat-vLLM delivered higher single-stream decode rates than Strata across all tested prompt lengths, including 124.9 versus 74.8 tokens per second at 2,654 tokens. It also led most prefill and concurrent-request tests, but Strata performed better on prefill near 100K tokens and generally achieved higher multi-token-prediction acceptance. The author says 1Cat-vLLM is a Tesla V100-focused vLLM fork with original expert-caching work.

In-depth insight

The results provide a practical community comparison of two inference engines running a quantized Qwen3.8-Flash-Next model on a multi-GPU Tesla V100 setup.

Edit: 1Cat-vLLM is a Tesla V100 focused fork of vLLM, and the expert caching work is 1Cat's original work, which may or may not one day make it to vLLM.

Everyday we see posts about speeds on Strata and its forks, but just recently I came to know that 1Cat has added support for expert caching recently, like a month ago. So I did (asked claude) a comparison of speeds on a Qwen3.8-Flash-Next UD-IQ3_XXS quant. My rig is 4x 16gb Tesla V100 on PCIe 3 x16 links, with 8 channel 3200 mt/s ddr4 ram, Epyc 7543 CPU. Now, for numbers:

Single stream

Median of 3 runs, except the 97k tokens one which I asked to run only once to save time.

Prompt (tokens)Prefill tok/s, StrataPrefill tok/s, 1CatDecode tok/s, StrataDecode tok/s, 1CatMTP acceptance, Strata / 1Cat
2,6548611,85074.8124.90.61 / 0.45
8,6741,1462,48379.3140.80.67 / 0.66
30,2992,4802,77676.4139.30.63 / 0.58
96,5883,3842,64977.2142.60.72 / 0.62

#1Cat-vLLM#Strata#vLLM#Qwen3.8-Flash-Next#Tesla V100#NVIDIA#EPYC 7543

Original · 3 min readRead the original
Group chat

No comments yet. Start the conversation.