Tao He e93f4cc9e3 Add the support for the qwen3 next model (a hybrid attention model). (#24526) ...

Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

2025-09-11 15:32:09 +08:00

..

__init__.py

Add the support for the qwen3 next model (a hybrid attention model). (#24526)

2025-09-11 15:32:09 +08:00

cache.py

[Core] Use sha256 bytes instead of BlockHash to reduce GC overhead (#23673)

2025-09-08 21:34:37 -07:00

compilation.py

Add the support for the qwen3 next model (a hybrid attention model). (#24526)

2025-09-11 15:32:09 +08:00

kv_events.py

Move KVEventsConfig from config/__init__.py to config/kv_events.py (#24433)

2025-09-08 06:41:27 -07:00

kv_transfer.py

Move KVTransferConfig from config/__init__.py to config/kv_transfer.py (#24434)

2025-09-08 20:30:32 -07:00

load.py

[Core] feat: Add --safetensors-load-strategy flag for faster safetensors loading from Lustre (#24469)

2025-09-10 23:10:01 -07:00

parallel.py

[Bugfix] Improve EPLB config validation error message (#24524)

2025-09-10 00:32:36 +00:00

scheduler.py

[V0 Deprecation] Remove args for multi-step scheduling (#22779)

2025-08-12 20:38:18 -07:00

utils.py

Extract CompilationConfig from config.py (#22524)

2025-08-08 16:34:25 -07:00