English translation is being prepared.
Matched fieldsSummary、Body
←Search results
Search “DeepSeek”
English translation is being prepared.
Matched fieldsSummary、Body
English translation is being prepared.
Matched fieldsSummary、Body
English translation is being prepared.
Matched fieldsSummary、Body
Baseten Engineering Blog Research Articles List: GLM-5 Inference Optimization and Legal Agent Training
The Baseten Engineering Blog research section features several articles, including "How we built the fastest GLM-5 on Artificial Analysis," post-training frontier legal agents in collaboration with Harvey, dark-free distillation, BYO SWE-grep automatic training of search sub-agents (Part 1), Lumina customer-in-the-loop self-improving evaluation, attention-based attribution, and robust sample-efficient SFT with prompt mutation. Popular models listed on the page include DeepSeek V4.1 Flash, GLM-5.3 Fast, GLM-5.3, GLM-5.3-Flash, Kimi K3, and Whisper Large V3.
articles, including "How we built the fastest GLM-5 on Artificial Analysis," post-training frontier legal agents in collaboration with Harvey, dark-free distillation, BYO SWE-grep automatic training of search sub-agents (Part 1), Lumina customer-in-the-loop self-improving evaluation, attention-based attribution, and robust sample-efficient SFT with prompt mutation. Popular models listed on the page include DeepSeek V4.1 Flash, GLM-5.3 Fast, GLM-5.3, GLM-5.3-Flash, Kimi K3, and Whisper Large V3.
Matched fieldsSummary、Body
Baseten Engineering Blog: Whisper Model Deployment and Popular Model List
The Baseten engineering blog lists several articles, including building with OpenAI's Whisper model in five minutes, the reasons behind an open-source model serving solution, and four ML models that accelerate content creation. The page also lists popular models: DeepSeek V4.1 Flash, GLM-5.3 Fast, GLM-5.3, GLM-5.3-Flash, Kimi K3, and Whisper Large V3.
Matched fieldsSummary、Body
English translation is being prepared.
Matched fieldsSummary、Body
English translation is being prepared.
Matched fieldsSummary、Body
English translation is being prepared.
Matched fieldsSummary、Body
English translation is being prepared.
Matched fieldsSummary、Body
English translation is being prepared.
Matched fieldsSummary、Body
English translation is being prepared.
Matched fieldsSummary、Body
English translation is being prepared.
Matched fieldsSummary、Body
English translation is being prepared.
Matched fieldsSummary、Body
Cerebras: Fast Inference Finds Its Rhythm
Cerebras looks back at 2025: DeepSeek R1 Llama 70B runs at over 1500 tokens/second on its chips, about 57 times that of GPUs; independent testing by Artificial Analysis shows its inference performance exceeds NVIDIA Blackwell's record. Cognition's SWE-1.5 and SWE-grep series achieve frontier-level coding performance at up to 13 times the speed of general-purpose models. Cerebras has launched a 40+ exaflop data center in Oklahoma and is deploying more than 7 data centers across North America and Europe.
Cerebras looks back at 2025: DeepSeek R1 Llama 70B runs at over 1500 tokens/second on its chips, about 57 times that of GPUs; independent testing by Artificial Analysis shows its inference performance exceeds NVIDIA Blackwell's record. Cognition's SWE-1.5 and SWE-grep series achieve frontier-level coding performance at up to 13 times the speed of general-purpose models. Cerebras has launched a 40+ exaflop data center in Oklahoma and is deploying more than 7 data centers across North America and
Matched fieldsSummary、Body
Baseten Engineering Blog: A Roundup of Model Performance Optimization Practices
The model performance section of the Baseten engineering blog rounds up several inference optimization efforts, including speeding up pyannote's speaker diarization model by 9.6x, speeding up Kimi K3 tokenization by 18x under million-token agent workloads, and performing inference engineering optimization for DeepSeek V4 Pro 0813. The section also covers delta weight synchronization optimization for hosted RL rollouts, Coval voice AI benchmarking, and the practice of building APIs for Kimi K3 and GLM-5.2.
performance section of the Baseten engineering blog rounds up several inference optimization efforts, including speeding up pyannote's speaker diarization model by 9.6x, speeding up Kimi K3 tokenization by 18x under million-token agent workloads, and performing inference engineering optimization for DeepSeek V4 Pro 0813. The section also covers delta weight synchronization optimization for hosted RL rollouts, Coval voice AI benchmarking, and the practice of building APIs for Kimi K3 and GLM-5.2.
Matched fieldsSummary、Body
Baseten Engineering Blog AI Models Article List
The AI Models section of the Baseten Engineering Blog brings together multiple articles on models and inference engineering, including NVIDIA Nemotron 3 Diarization, which achieves real-time speaker labeling at one cent per audio hour; DeepSeek-V4.1-Flash, which offers more efficient prefill for coding agents; and introductions to new models such as NVIDIA Nemotron 3.5 Lightning, Nemotron 3.5 ASR Streaming, and Nemotron 3 Embed. It also covers topics such as GLM-5.3 post-training scaling, GLM 5.2 vision capabilities, Laguna S 2.1, and recommendations for open-source post-trained models.
ings together multiple articles on models and inference engineering, including NVIDIA Nemotron 3 Diarization, which achieves real-time speaker labeling at one cent per audio hour; DeepSeek-V4.1-Flash, which offers more efficient prefill for coding agents; and introductions to new models such as NVIDIA Nemotron 3.5 Lightning, Nemotron 3.5 ASR Streaming, and Nemotron 3 Embed. It also covers topics such as GLM-5.3 post-training scaling, GLM 5.2 vision capabilities, Laguna S 2.1, and recommendations
Matched fieldsSummary、Body
English translation is being prepared.
Matched fieldsSummary、Body
English translation is being prepared.
Matched fieldsSummary、Body
After Nvidia chips became hard to buy, what keeps China's large models running?
A Huxiu analysis points out that domestic computing power can now cover large model operation: Zhipu's domestic-chip inference cluster has reached a scale of 100,000 cards, and Meituan's LongCat-2.0 has also completed training on domestic computing power. However, Ascend 910C achieves an MFU of about 30%-35% in trillion-parameter post-training, lower than H100's 40%-50%. The article breaks computing efficiency into three variables—chips, software, and models—and compares the four paths of Zhipu, MiniMax, DeepSeek, and Kimi, concluding that Zhipu has the highest short-term certainty, while DeepSeek has the greatest medium-term elasticity. The author proposes three tracking indicators—capacity, efficiency, and cost—and argues that only when all three improve simultaneously can domestic computing power shift from a backup option to a cost advantage.
r post-training, lower than H100's 40%-50%. The article breaks computing efficiency into three variables—chips, software, and models—and compares the four paths of Zhipu, MiniMax, DeepSeek, and Kimi, concluding that Zhipu has the highest short-term certainty, while DeepSeek has the greatest medium-term elasticity. The author proposes three tracking indicators—capacity, efficiency, and cost—and argues that only when all three improve simultaneously can domestic computing power shift from a backup
Matched fieldsSummary、Body