DeepSeek-Coder-V2
❖ We present DeepSeek-Coder-V2, an open-source Mixture-of-Experts (MoE) code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks. It is further pre-trained from an intermediate checkpoint of DeepSeek-V2 with additional 6 trillion tokens. Through this continued pre-training, DeepSeek-Coder-V2 substantially enhances the coding and mathematical reasoning capabilities of DeepSeek-V2, while maintaining comparable performance in general language tasks.
Qwen2
❖ After months of efforts, we are pleased to announce the evolution from Qwen1.5 to Qwen2. This time, we bring to you: Pretrained and instruction-tuned models of 5 sizes, including Qwen2-0.5B, Qwen2-1.5B, Qwen2-7B, Qwen2-57B-A14B, and Qwen2-72B; State-of-the-art performance in a large number of benchmark evaluations; Significantly improved performance in coding and mathematics; Extended context length support up to 128K tokens with Qwen2-7B-Instruct and Qwen2-72B-Instruct.
DeepSeek-V2
❖ We introduce DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. It comprises 236B total parameters, of which 21B are activated for each token. Compared with DeepSeek 67B, DeepSeek-V2 achieves stronger performance, and meanwhile saves 42.5% of training costs, reduces the KV cache by 93.3%, and boosts the maximum generation throughput to more than 5 times.
Accelerating Self-Attentions for LLM Serving with FlashInfer
❖ The efficacy of operators within Transformers – namely GEMM, Self-Attention, GEMV, and elementwise computations are critical to the overall performance of LLM (Large Language Models) serving. While optimization efforts have extensively targeted GEMM and GEMV, there is a lack of performance studies focused on Self-Attention in the context of LLM serving. In this blog post, we break Self-Attention down into three stages: prefill, decode, and append; analyze the performance bottleneck of Self-Attention on both single-request and batching scenarios in these three stages; and propose a solution to tackle these challenges.
SGLang
❖ Large Language Models (LLMs) are increasingly utilized for complex tasks that require multiple chained generation calls, advanced prompting techniques, control flow, and interaction with external environments. However, there is a notable deficiency in efficient systems for programming and executing these applications. To address this gap, we introduce SGLang, a Structured Generation Language for LLMs. SGLang enhances interactions with LLMs, making them faster and more controllable by co-designing the backend runtime system and the frontend languages.
DeepSeek MoE
❖ DeepSeekMoE 16B is a Mixture-of-Experts (MoE) language model with 16.4B parameters. It employs an innovative MoE architecture, which involves two principal strategies: fine-grained expert segmentation and shared experts isolation. It is trained from scratch on 2T English and Chinese tokens, and exhibits comparable performance with DeepSeek 7B and LLaMA2 7B, with only about 40% of computations.
Reasoning with Foundation Models
❖ We organize the current foundation models into three categories: language foundation models, vision foundation models, and multimodal foundation models. Further, we elaborate the foundation models in reasoning tasks, including commonsense, mathematical, logical, causal, visual, audio, multimodal, agent reasoning, etc. Reasoning techniques, including pre-training, fine-tuning, alignment training, mixture of experts, in-context learning, and autonomous agent, are also summarized.
Mixture of Experts Explained
❖ With the release of Mixtral 8x7B (announcement, model card), a class of transformer has become the hottest topic in the open AI community: Mixture of Experts, or MoEs for short. In this blog post, we take a look at the building blocks of MoEs, how they’re trained, and the tradeoffs to consider when serving them for inference.