Expired60% confidenceFactExact time
DeepSeek V3 versions prior to 0324 had an infinite loop call issue with Function Calling, which was fixed in version 0324 and later.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/7/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/5/2026(expired)
Sources
LangChain+MCP实战：大模型选型与本地部署避坑指南
bilibili码士集团-马小琪7/5/2026
Related Claims
UnverifiedvLLM v0.29.0rc4 fixed a bug in TensorRT-LLM ragged prefill scenarios that avoided unnecessary synchronization.64% similarUnverifiedVersion v0.28.0rc1 fixes the loading logic of _load_ov2_processor by introducing the resolve_trust_remote_code guard mechanism.61% similarUnverifiedQwen3 27B's performance on coding and agent benchmarks is: SWE-bench Pro 61.7, Terminal-Bench 2.1 73.0, and LiveCodeBench V6 90.3.60% similarUnverifiedDeepSeek released the first visual version weights of V4, with a model scale of 305B (approximately 305 billion parameters), along with a minimal inference implementation.60% similarUnverifiedThe performance issue originates from commit #15486 in the ComfyUI repository, submitted by core developer comfyanonymous, titled "Fix peak memory issue with H3".59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/131913API
curl https://kongchang.com/api/v1/knowledge/claims/131913MCP
get_claim(id=131913)