Unverified50% confidenceBenchmarkExact time
BasisKV achieves up to 1.42x end-to-end speedup under 8-GPU tensor parallel inference.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/3/2026
First Seen
Valid until: 2/1/2027
Sources
Related Entities
Related Claims
UnverifiedWhen mainstream inference engines run this model on the same hardware, the speed is generally stuck in the 6–8 FPS range.75% similarUnverifiedOn NVIDIA GPUs, the geometric mean speedup of the full low-level backward pass is 1.15–1.81×.70% similarUnverifiedIn the UP host's real-world tests, the generation speed was over 90 tokens per second under a 64K context, dropping to over 60 tokens per second under a 256K context.69% similarUnverifiedOn a consumer-grade GPU with 8GB of VRAM, ActionAssist achieves an inference speed of 122 tokens/second using Q6_K_L quantization with a 32k context window and 8-bit KV cache quantization.68% similarUnverifiedThe theoretical peak of a 56k dial-up modem is approximately 7KB per second.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1130475API
curl https://kongchang.com/api/v1/knowledge/claims/1130475MCP
get_claim(id=1130475)