amote-i 70a813493f [NPU] [DOC] add missing DEEP_NORMAL_MODE_USE_INT8_QUANT for w8a8+deepep scenarios (#29937)

2026-07-03 10:18:22 +08:00

..

advanced_features

feat(mem_cache): unified memory pool for hybrid Mamba / SWA models (#29678)

2026-07-01 13:21:59 -07:00

basic_usage

[Docs] Add Anthropic-compatible API documentation (#28522)

2026-06-22 04:01:09 +00:00

developer_guide

update quantization code owner and document quantization contributions (#26784)

2026-06-26 19:40:33 +03:00

get-started

[Docs] Add --prerelease=allow so uv installs the latest sglang (#29676)

2026-06-29 14:13:34 -07:00

hardware-platforms

[NPU] [DOC] add missing DEEP_NORMAL_MODE_USE_INT8_QUANT for w8a8+deepep scenarios (#29937)

2026-07-03 10:18:22 +08:00

references

[misc] Use --cuda-graph-max-bs-decode in tests, examples, and docs (#29591)

2026-06-28 18:38:28 -07:00

sglang-diffusion

[diffusion] Add Qwen-Image ModelOpt NVFP4 support (#28928)

2026-06-25 22:56:09 +08:00

supported-models

model: support nvidia/LocateAnything-3B (#28958)

2026-06-30 00:16:42 +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