Image created with Gemini. Image prompt: Hand-painted Studio Ghibli style square cover of a sunlit seaside curio shop window displaying a smiling porcelain whale-shaped mask with rose-blush cheeks, tilted to reveal an inner lattice of glowing blue circuitry and tiny brass gears, a warm wooden shop sign above reading DeepSeek in bold clean legible letters, terracotta rooftops and teal harbor beyond, soft gouache watercolor backgrounds, gentle golden-hour light, cozy but quietly mysterious mood.
We’ve been impressed with GLM-5.2 and so are introducing a $9.99/month subscription to give you 2-5x discounted access to it and other open weight models like DeepSeek, Kimi, MiniMax, Mimo, Qwen. Use it on Cline CLI & IDE with $1.99 special promo if sign up via: npm i -g cline”
https://x.com/cline/status/2071617325296734309
Sonnet 5 goes straight into the garbage bin > 1.2x more expensive than Opus 4.8 Max > 2x more expensive than GPT-5.5-xhigh > 5x more expensive than GLM-5.2 > 7x more expensive than Kimi-K2.6 > 57x more expensive than DeepSeek-V4-Pro”
https://x.com/scaling01/status/2072071305281540338
> the improvement over DFlash: > +20% acceptance length > +14% throughput > avg 127 tok/s vs 111 for DFlash and 81 for EAGLE-3 > for single GPU inference, DSpark’s lightweight + early stopping approach is clearly superior …DeepSeek did just casually ship a SoTA spec decoding”
https://x.com/teortaxesTex/status/2071631028511203457
AI concepts and techniques of 2026 ▪️ DeepSeek mHC ▪️ Conditional memory and selective intelligence ▪️ The new fine-tuning stack for LLMs: advanced LoRA + Evolution Strategies ▪️ On-policy self-distillation ▪️ New chips: MatX, Taalas, and the Cracks in the GPU Era ▪️”
https://x.com/TheTuringPost/status/2072483002333200788
We’re about to start seeing feats that are less heroic and more scary. By the fourth week of July 2026, we are likely to see: – DeepSeek-V4-official – Huawei Ascend 950DT SuperPOD (likely beats Meituan’s whole cluster) – ZQ-3 landing (less certain) takeoff begins?”
https://x.com/teortaxesTex/status/2071889274954260720
I wonder how much economic value DeepSeek has just created with DSpark. Imagine if *every* Chinese provider improves throughput by 50% 3 months faster. Or improves interactivity by 60%. And anything in between. Billions?”
https://x.com/teortaxesTex/status/2071873225881989424
Why DeepSeek’s DSpark matters: cheaper, faster inference may be the real AI bottleneck 🌟A clear take from Zhihu contributor 平凡 on why DSpark is less about headline model capability and more about making powerful AI usable at scale. TL;DR: DSpark does not make the model”
https://x.com/ZhihuFrontier/status/2071445817102315595
👀 vLLM community is working non-stop to get @deepseek_ai’s new DSpark spec decode algorithm for vLLM! Faster inference for everyone!
https://x.com/vllm_project/status/2071682507775635579
🚀 @deepseek_ai’s DSpark speculative decoding now runs natively in vLLM! What it is: a semi-autoregressive drafter that proposes several tokens in parallel with non-causal sliding-window attention, then verifies them in a single pass. Output stays identical, decoding takes fewer”
https://x.com/vllm_project/status/2072545387639189798
DeepSeek is the forever goat on ML infras. If they haven’t open source all the god-like AI infra projects like DeepSpec / DeepEP / DeepGEMM, we’ll forever be puzzling on why they can achieve super low cost and super high throughput per stream yet still be profitable. As I”
https://x.com/Xianbao_QIAN/status/2071917185380073611
DeepSeek open sources DSpark, a new framework to speed up LLM inference by up to 85% | VentureBeat
https://venturebeat.com/orchestration/deepseek-open-sources-dspark-a-new-framework-to-speed-up-llm-inference-by-up-to-85
GLM 5.2 DSpark preview is here! ✨
https://t.co/DQOMYEiY1o This is the first DSpark speculator for a non-DeepSeek frontier model, trained with Speculators and running on vLLM nightly for ~1.5× faster decode for GLM-5.2-FP8 on 4×B300. Stronger checkpoints to come!”
https://x.com/mgoin_/status/2072525522639212825
Leave a Reply