3 people f05c92fb6d ✨ [llm][npu][quant] Add W8A8 MXFP8 quantization for Qwen3 MoE on Ascend NPU (#30768) ...

Co-authored-by: Артем Савкин <58187114+OrangeRedeng@users.noreply.github.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>

2026-07-29 10:39:36 +03:00

..

advanced_features

✨ [llm][npu][quant] Add W8A8 MXFP8 quantization for Qwen3 MoE on Ascend NPU (#30768)

2026-07-29 10:39:36 +03:00

basic_usage

Remove legacy Sphinx docs/ and finish the Mintlify cutover (#28964)

2026-07-13 15:06:08 -07:00

developer_guide

[Kernel] RFC #29630 finale: retire sglang.jit_kernel into sglang.kernels (#32072)

2026-07-23 08:35:09 +08:00

get-started

chore: bump docs install version to 0.5.16 (#32347)

2026-07-24 17:19:39 -07:00

hardware-platforms

✨ [llm][npu][quant] Add W8A8 MXFP8 quantization for Qwen3 MoE on Ascend NPU (#30768)

2026-07-29 10:39:36 +03:00

references

[PD] Prevent decode scheduler from blocking on ZMQ sends to a stalled prefill peer (#31144)

2026-07-25 12:53:41 +08:00

sglang-diffusion

docs: clarify diffusion stage reuse guidance (#32639)

2026-07-28 19:52:52 +08:00

supported-models

model: serve bare Qwen3Model backbone natively as an embedding model (#32457)

2026-07-27 15:49:58 +08:00

supported-models.mdx

[Docs] Sync docs_new with legacy docs and update migration redirects (#23337)

2026-04-21 00:15:17 -07:00