#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
- DeepSeek rolls out peak/off-peak pricing on V4-Pro, effective Aug 16 16:00 UTC DeepSeek tools
- DeepSeek releases experimental multimodal V4-Flash-Vision-Exp 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
- llama.cpp v0.3.0 — first tagged stable release of the b10621 nightly; dots3-note multimodal, GLM-4.5-Air MTP, DeepSeek 4 tensor-split, ggml v0.22.0 ggml-org tools
- DeepSeek V4 — API price cuts DeepSeek models-llm
- vLLM v0.20.1 Patches Critical DeepSeek V4 Instability Under Production Workloads vLLM Project tools
- Cline ships v4.1.13/14/15 with model catalog refresh, MCP auto-approve fix and `cline hub` drain/upgrade commands Cline tools
- llama.cpp b10603-b10615 — GLM-4.5-Air MTP, Deepseek 4 -sm tensor, Metal flash-attn vec tuning for M1 Pro/M2 Ultra/M5 Max ggml-org tools