|
About the Benchmarking category
|
|
0
|
46
|
March 20, 2025
|
|
Transformers `do_sample=False` vs SamplingParms `temperature=0` gives different results
|
|
1
|
110
|
November 15, 2025
|
|
VLLM 0.10.1 benchmark do not free memory
|
|
13
|
81
|
November 10, 2025
|
|
Vllm bench serve not all requests are successful. whats the reason?
|
|
5
|
138
|
October 23, 2025
|
|
How can I disable the model forward pass to measure host-only (CPU) overhead?
|
|
5
|
20
|
October 21, 2025
|
|
Vllm bench serve Order of "generated_texts"
|
|
16
|
59
|
October 6, 2025
|
|
Logprobs output from vllm bench serve
|
|
6
|
130
|
September 27, 2025
|
|
Running vllm bench serve from CPU-only node
|
|
3
|
520
|
August 29, 2025
|
|
Num request running stays on 1
|
|
3
|
152
|
August 29, 2025
|
|
Mixedbread reranker on vLLM `/score`: scores differ vs local Mixedbread; small payload = same order/different scores, large payload = different order
|
|
1
|
40
|
August 15, 2025
|
|
Vllm bench serve + Bearer API key + HTTPS
|
|
1
|
240
|
August 7, 2025
|
|
使用以下2种方式，获得的结果有很大差异
|
|
50
|
1092
|
July 25, 2025
|
|
High-Throughput kernel on single-node
|
|
1
|
125
|
June 23, 2025
|
|
VLLM Engine Metrics
|
|
20
|
270
|
June 11, 2025
|
|
vLLM benchmark host with self-signed certificate
|
|
1
|
167
|
June 4, 2025
|
|
ShareGPT implementation
|
|
1
|
477
|
May 22, 2025
|