A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[Misc] Add claude settings to gitignore (#24492)
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Ye (Charlotte) Qi committed
Sep 9, 2025 at 01:14 UTC
45c9cb583564744e25e37b3d4ffd10958788c5b2
1 file changed
+6
-2
.gitignore
+6
-2
@@ -4,7 +4,7 @@
4
# vllm-flash-attn built from source
5
vllm/vllm_flash_attn/*
6
7
-# triton jit
7
+# triton jit
8
.triton
9
10
# Byte-compiled / optimized / DLL files
@@ -177,6 +177,10 @@ cython_debug/
177
# VSCode
178
.vscode/
179
180
+# Claude
181
+CLAUDE.md
182
+.claude/
183
+
184
# DS Store
185
.DS_Store
186
@@ -209,4 +213,4 @@ shellcheck*/
213
csrc/moe/marlin_moe_wna16/kernel_*
214
215
# Ignore ep_kernels_workspace folder
212
-ep_kernels_workspace/
\ No newline at end of file
216
+ep_kernels_workspace/