Ascend NPU fork of nanochat for LLM training with torch_npu/HCCL (experimental)
-
Updated
Feb 24, 2026 - Python
#
torch-npu
Here are 4 public repositories matching this topic...
Mini-SGLang port for Ascend NPUs with FIA, paged KV cache, ragged continuous batching, and request lifecycle safety.
inference-engine ascend kv-cache llm llm-serving llm-inference ascend-npu qwen paged-attention sglang continuous-batching torch-npu mini-sglang
-
Updated
Jul 12, 2026 - Python
Run nanochat training efficiently on Huawei Ascend NPUs with minimal code changes, supporting tokenizer, pretraining, and evaluation workflows.
-
Updated
Aug 15, 2026 - Python
Native AscendC Mamba2 selective scan / SSD forward-backward custom operator for Huawei Ascend 910B3 and 950PR, with CANN, torch_npu, A100 benchmarks and msprof profiling.
pytorch ssd mamba cann performance-optimization state-space-models ascend-npu selective-scan ai-infrastructure ascendc kernel-optimization mamba2 huawei-ascend torch-npu custom-operator ascend-910b triton-ascend ascend-950
-
Updated
Aug 12, 2026 - Python
Improve this page
Add a description, image, and links to the torch-npu topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the torch-npu topic, visit your repo's landing page and select "manage topics."