Unverified50% confidenceBenchmarkExact time
In the 30-token configuration, the approach is 8.8× faster than Program-of-Thought and 2.8× more energy-efficient.
1
Sources
50%
Confidence
Long-term
Relevance
9/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOpenCode Go's weekly call count is 1.56 times more than Ollama's, and its token count is 1.64 times more.65% similarUnverifiedThe VAE decoding speed of LTX-2 was improved by 1.41x, while saving 9.7 GiB of peak VRAM usage.64% similarUnverified当上下文长度超过3万token时，4×16G与2×32G两种方案的预处理速度曲线逐渐贴合63% similarUnverifiedIn a prefill-only test running gpt-oss-120b on 4× B200s, DWDP4 achieves a 1.92× speedup over DEP4 under the MNT 32K/ISL 32K configuration and a 1.54× throughput improvement at saturation (506K vs. 329K tok/s).63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/960995API
curl https://kongchang.com/api/v1/knowledge/claims/960995MCP
get_claim(id=960995)