DeepSeek and Huawei released open-source programming tools for Huawei's Ascend accelerators, announced on DeepSeek's WeChat account on Wednesday, including compute libraries, chip-to-chip communicatio…
DeepSeek and Huawei Technologies unveiled a suite of open-source programming tools for Huawei's Ascend AI chips on September 30, 2026, centered on TileLang, a high-level language pitched as a simpler …
Laya released a multilingual, non-autoregressive "System 1" decision engine that returns typed decisions across 100+ languages in a single forward pass in 33 ms, installable via `python -m pip install…
Deepseek and Huawei have released open-source programming tools for Huawei's Ascend AI chips, centered on TileLang, a language designed to offer a simpler programming model than Nvidia's CUDA. The par…
DeepSeek said on Wednesday it has partnered with Huawei Technologies to develop and open-source programming infrastructure for Huawei's Ascend chips, including compute and communication libraries, as …
A homelab user deploying DeepSeek-V4-Flash-0731 on two DGX Spark units achieved 1M token context with an NVFP4 KV cache using a custom vLLM fork, reporting a KV cache size of 1,492,347 tokens and maxi…
TileLang, a high-level Python domain-specific language for designing GPU kernels through TVM, enables developers to implement tensor-core GEMM, fused softmax, FlashAttention, and autotuning while mana…
NVIDIA's C++ template-based CUTLASS library for GPU kernels suffers from compile times of up to 20 seconds for a single kernel and over 17 minutes for full builds, prompting a shift toward Python-embe…
TileLang introduces a middle-ground approach for writing high-performance GPU kernels, offering explicit control over shared memory allocation, pipeline staging, and warp partitioning through Python c…