60e2be1b36
[RFC](https://github.com/vllm-project/vllm-ascend/issues/3328) for more details. Add dynamic batch feature in chunked prefilling strategy, the token budget can be refined to achieve better effective throughput and TPOT. !!! NOTE: only 910B3 is supported till now, we are working on further improvements. Additional file for lookup table is required. - vLLM version: v0.11.0rc3 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0 --------- Signed-off-by: Cheng Wang <wangchengkyrie@outlook.com>
37 lines
901 B
TOML
37 lines
901 B
TOML
[build-system]
|
|
# Should be mirrored in requirements.txt
|
|
requires = [
|
|
"cmake>=3.26",
|
|
"decorator",
|
|
"einops",
|
|
"numpy<2.0.0",
|
|
"packaging",
|
|
"pip",
|
|
"pybind11",
|
|
"pyyaml",
|
|
"scipy",
|
|
"pandas",
|
|
"pandas-stubs",
|
|
"setuptools>=64",
|
|
"setuptools-scm>=8",
|
|
"torch-npu==2.7.1.dev20250724",
|
|
"torch>=2.7.1",
|
|
"torchvision",
|
|
"wheel",
|
|
"msgpack",
|
|
"quart",
|
|
"numba",
|
|
]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[tool.pymarkdown]
|
|
plugins.md004.style = "sublist" # ul-style
|
|
plugins.md007.indent = 4 # ul-indent
|
|
plugins.md007.start_indented = true # ul-indent
|
|
plugins.md013.enabled = false # line-length
|
|
plugins.md041.enabled = false # first-line-h1
|
|
plugins.md033.enabled = false # inline-html
|
|
plugins.md046.enabled = false # code-block-style
|
|
plugins.md024.allow_different_nesting = true # no-duplicate-headers
|
|
plugins.md029.enabled = false # ol-prefix
|