English translation is being prepared.
Matched fieldsSummary
←Search results
Search “NVIDIA”
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
LMSYS explains in detail how HiCache adapts to multi-parallelism and distributed inference
The LMSYS blog introduces how HiCache is implemented in context parallelism, pipeline parallelism, speculative decoding, unified KV layout, and P/D disaggregation scenarios, with the core being to keep cache decisions consistent across ranks. The iFlytek Spark MaaS team used HiCache plus external storage to serve GLM-5.1/5.2 CodingPlan workloads, raising the cache hit rate from about 30% to 95% and reducing median TTFT to under 3 seconds. In CP sharding tests, the GPU token hit rate increased by 40.48 percentage points, the host memory serving token volume dropped by 81.2%, and the average prefill queueing time decreased by 56.2%.
The LMSYS blog introduces how HiCache is implemented in context parallelism, pipeline parallelism, speculative decoding, unified KV layout, and P/D disaggregation scenarios, with the core being to keep cache decisions consistent across ranks. The iFlytek Spark MaaS team used HiCache plus external storage to serve GLM-5.1/5.2 CodingPlan workloads, raising the cache hit rate from about 30% to 95% and reducing median TTFT to under 3 seconds. In CP sharding tests, the GPU token hit rate increased by
Matched fieldsBody
Building Efficient Agents with Knowledge Distillation on Amazon SageMaker AI
An AWS official blog post explains how to fine-tune a shopping agent on Amazon SageMaker AI using sequence-level knowledge distillation (SeqKD): using GLM-5.3 on Amazon Bedrock as the teacher model to generate trajectories, using the ShoppingBench scorer to retain only trajectories that solve the task, and then performing serverless SFT on the Qwen3.5-4B student model. On 324 held-out test questions, the distilled 4B student's average absolute success rate increased from 0.297 to 0.541, essentially on par with the teacher model and mid-sized frontier models; when the teacher's reasoning process was removed and only tool calls were learned, the average success rate dropped to 0.415.
An AWS official blog post explains how to fine-tune a shopping agent on Amazon SageMaker AI using sequence-level knowledge distillation (SeqKD): using GLM-5.3 on Amazon Bedrock as the teacher model to generate trajectories, using the ShoppingBench scorer to retain only trajectories that solve the task, and then performing serverless SFT on the Qwen3.5-4B student model. On 324 held-out test questions, the distilled 4B student's average absolute success rate increased from 0.297 to 0.541, essentia
Matched fieldsBody
Latent Space announces AIE CODE coding agent conference curation themes
Latent Space host swyx introduces the curation approach for the annual flagship conference AIE CODE, which is single-track, invitation-only, and aimed at about 1,000 agent engineers. This year's three themes are Scaling without Slop, System One models, and Increasing Ambition, among which Jarred Sumner will share Bun's rewrite in Rust and a Bun AOT preview. The article also rounds up that day's AI news, including Mistral's open-weight release and OpenAI's frontier model monitoring.
Matched fieldsBody
Edge0 Releases Audio8-TTS-Realistic: A 0.6B Open-Source Voice Cloning TTS Model
Edge0 has released the open-weight voice cloning TTS model Audio8-TTS-Realistic, with 601M parameters, supporting 23 languages, with weights and code released under Apache 2.0. The model requires only 1 reference audio clip and its corresponding text for zero-shot voice cloning, and can also directly generate speech when no reference voice is available. Self-reported results show an average error rate of 4.86% on the CV3 nine-language benchmark, lower than Qwen3-TTS-1.7B's 7.73%, but it lags behind 4B-class models on the MiniMax benchmark, with Thai WER reaching 48.57%.
Edge0 has released the open-weight voice cloning TTS model Audio8-TTS-Realistic, with 601M parameters, supporting 23 languages, with weights and code released under Apache 2.0. The model requires only 1 reference audio clip and its corresponding text for zero-shot voice cloning, and can also directly generate speech when no reference voice is available. Self-reported results show an average error rate of 4.86% on the CV3 nine-language benchmark, lower than Qwen3-TTS-1.7B's 7.73%, but it lags beh
Matched fieldsBody
October 28 AI Daily Brief: Genie 4 and MAI-Image-2.7 Released
Google DeepMind released the interactive world model Genie 4, which supports natural language control and native audio. It is first being opened to Trusted Testers, with later integration into Google AI Ultra and the Gemini API. Microsoft AI launched the image editing model MAI-Image-2.7-Preview, ranking 3rd on Arena Edit and 2nd on AA-Image-Editing. Liquid AI open-sourced the LFM3 series of six 2B-class text, vision, audio, and omni-modal models, using a triple-hybrid architecture.
Matched fieldsBody