|
55c4853487
|
[comm] Enable multi-node custom-AR v2 on a single NVLink clique (#32339)
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
|
2026-07-25 17:25:18 -07:00 |
|
|
Ming YangandClaude
|
9b4bb415dd
|
[cuda-graph] Size breakable-graph shared buffer from warmup output; slice by produced row count (#30834)
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-07-11 10:41:44 -07:00 |
|
|
Ming Yang
|
5ae214f18b
|
Extract reusable VMM shareable-handle helpers from register_graph_inputs (#29621)
|
2026-07-01 14:02:00 -07:00 |
|
|
Ming Yang
|
85471d253d
|
Add --disable-attn-tp-gather opt-out for model-managed SP (#26047)
|
2026-05-24 15:53:51 -07:00 |
|
|
Ming Yang
|
6bb79c155b
|
[Linear Attn] Add CUSTOM enum and plugin extensibility for kernel backends (#24937)
|
2026-05-11 21:46:53 -07:00 |
|
|
Ming Yang
|
7b10f01d1c
|
[model_runner] Label forward steps in profile traces with mode and token counts (#23419)
|
2026-04-22 02:31:18 -07:00 |
|