Unverified50% confidenceBenchmarkExact time
On the B300 benchmark, Kimi K3's new optimization solution on vLLM achieved a 2.2 to 2.8× throughput improvement compared to version v0.27.1.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/17/2026
First Seen
Valid until: 12/16/2026
Sources
Related Entities
Related Claims
UnverifiedKimi K3 on AMD MI355X using grouped-head MLA verification kernels achieves 1.37–1.77× throughput improvement and 1.45–2.42× ITL improvement at concurrencies of 2–32.75% similarUnverifiedAccording to the documentation, Kimi K2.8 performs at a level comparable to K3 but has more efficient reasoning capabilities, supporting a 1-million-token context window, image and video input, and three reasoning modes: low, high, and max.70% similarUnverifiedAccording to official data, K3 achieves approximately a 2.5× improvement in overall inference efficiency compared to K2.67% similarUnverifiedKimi K3's 2.8 trillion parameter scale surpasses the previously largest open-weight model, DeepSeek-V3, which had 671 billion parameters.66% similarUnverifiedBoth Kimi K2.7 and GLM 5.2 achieved excellent results on the FrontierCode Extended benchmark.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/929843API
curl https://kongchang.com/api/v1/knowledge/claims/929843MCP
get_claim(id=929843)