wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-06-27 17:32:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Kernel] Refactor CUTLASS kernels to always take scales that reside on the GPU (#5137)

Browse Source
This commit is contained in:
Tyler Michael Smith
2024-06-01 02:45:32 -04:00
committed by GitHub
parent a360ff80bb
commit 260d119e86
7 changed files with 445 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pyproject.toml
+1 -1
View File
@@ -59,7 +59,7 @@ exclude = [
]
[tool.codespell]
ignore-words-list = "dout, te, indicies"
ignore-words-list = "dout, te, indicies, subtile"
skip = "./tests/prompts,./benchmarks/sonnet.txt,./tests/lora/data,./build"
[tool.isort]