 RuohengMa
|
de0c5e68fb
|
[XPU] Split the block_attn operator into smaller operators (#6798)
* spliced block_attn
* adapt to latest vllm
* fix unit tests
* delete mtp+cudagraph 4 cards test
* fix vl model
* fix mtp
* fix slot mapping
|
2026-04-16 14:28:40 +08:00 |
|