#deepseek-v4
- DeepSeek V4: official open-source release with Day-0 adaptation for Huawei Ascend DeepSeek models-llm
- DeepSeek Open-Sources DSpark: 57–85% Inference Speedup for V4 in Production DeepSeek tools
- DeepSeek V4 Stable Release Set for Mid-July with First Time-of-Day API Pricing DeepSeek models-llm
- DeepSeek Confirms V4 Official Launch for Mid-July with Peak-Time API Pricing DeepSeek models-llm
- DeepSeek V4 Graduates from Preview to General Availability with Peak-Hour API Pricing DeepSeek models-llm
- SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD SLAI research
- vLLM v0.24.0: Model Runner V2 Default, Rust Frontend, SM90 FP8 Speedups vLLM tools
- SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD SLAI research
- DeepSeek V4 — API price cuts DeepSeek models-llm
- vLLM v0.20.1 Patches Critical DeepSeek V4 Instability Under Production Workloads vLLM Project tools