EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

add env vars & misc

Browse Source
This commit is contained in:
starkwj
2026-02-11 06:27:58 +00:00
parent 739d074b0c
commit 389030a8f8
128 changed files with 89 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm_ascend/patch/platform/patch_executor.py
View File

@@ -43,11 +43,11 @@ def reload_vram(self) -> bool:
time.sleep(0.001)
def determine_available_memory_idle_offload_mode(self) -> int:
return self.collective_rpc("determine_available_memory_idle_offload_mode")
def determine_available_memory_vnpu_offload_mode(self) -> int:
return self.collective_rpc("determine_available_memory_vnpu_offload_mode")
ExecutorBase.__init__ = init
ExecutorBase.offload_vram = offload_vram
ExecutorBase.reload_vram = reload_vram
ExecutorBase.determine_available_memory_idle_offload_mode = determine_available_memory_idle_offload_mode
ExecutorBase.determine_available_memory_vnpu_offload_mode = determine_available_memory_vnpu_offload_mode