List your company

LLM Inference Scheduling on LMSYS-Chat-1M

0.1432Average Per-token Latency (s/token)Oracle SJF
-0.2142822.1986564.6115957.024534Sep 25, 2025Oct 26, 2025Nov 26, 2025Dec 28, 2025Jan 28, 2026Feb 28, 2026Apr 1, 2026

Evaluation results

MethodLinks
Oracle SJFModel=Llama2025.090.1432———
Oracle SJFModel=DeepSeek-R12025.090.1532———
PARSModel=Llama2025.090.1864———
Cross-Model PARSModel=Llama2025.090.1879———
PARSModel=DeepSeek-R12025.090.2069———
Listwise SJFModel=Llama2025.090.2146———
Cross-Model PARSModel=DeepSeek-R12025.090.2559———
Listwise SJFModel=DeepSeek-R12025.090.2749———
Pointwise SJFModel=DeepSeek-R12025.090.3217———
Pointwise SJFModel=Llama2025.090.3427———
FCFSModel=DeepSeek-R12025.090.521———
FCFSModel=Llama2025.091.2699———
TIETesting Model Size=70B, Request Rate (RPS)=100, Training Dataset=LMSYS-Chat-1M (8B)2026.042.414.05204.03475.1
LTRTesting Model Size=70B, Request Rate (RPS)=100, Training Dataset=LMSYS-Chat-1M (8B)2026.044.347.03252.2507.35
SSJFTesting Model Size=70B, Request Rate (RPS)=100, Training Dataset=LMSYS-Chat-1M (8B)2026.045.58.24273.3551.15
FCFSTesting Model Size=70B, Request Rate (RPS)=100, Training Dataset=LMSYS-Chat-1M (8B)2026.049.0816.13319.51618.21
Cross-Model PARSModel=DeepSeek-R1, Workload Mode=Burst Mode2025.09—0.5485——
Cross-Model PARSModel=Llama, Workload Mode=Burst Mode2025.09—0.2621——
FCFSModel=DeepSeek-R1, Workload Mode=Burst Mode2025.09—1.0911——
FCFSModel=Llama, Workload Mode=Burst Mode2025.09—2.3075——
Listwise SJFModel=DeepSeek-R1, Workload Mode=Burst Mode2025.09—0.5855——
Listwise SJFModel=Llama, Workload Mode=Burst Mode2025.09—0.3061——
Oracle SJFModel=DeepSeek-R1, Workload Mode=Burst Mode2025.09—0.259——
Oracle SJFModel=Llama, Workload Mode=Burst Mode2025.09—0.2088——
PARSModel=DeepSeek-R1, Workload Mode=Burst Mode2025.09—0.4226——
PARSModel=Llama, Workload Mode=Burst Mode2025.09—0.261——
Pointwise SJFModel=DeepSeek-R1, Workload Mode=Burst Mode2025.09—0.6668——
Pointwise SJFModel=Llama, Workload Mode=Burst Mode2025.09—0.5535——