adapt custom allreduce for tensorrt llm (#2511)
This commit is contained in:
@@ -27,7 +27,7 @@ runtime_common = [
|
||||
]
|
||||
srt = [
|
||||
"sglang[runtime_common]", "cuda-python",
|
||||
"sgl-kernel>=0.0.2.post12", "torch", "vllm>=0.6.3.post1,<=0.6.4.post1",
|
||||
"sgl-kernel>=0.0.2.post14", "torch", "vllm>=0.6.3.post1,<=0.6.4.post1",
|
||||
"flashinfer==0.1.6"
|
||||
]
|
||||
|
||||
|
||||
Reference in New Issue
Block a user