fix(moe): relocate orphan tuned configs after #23019 (#24004)

This commit is contained in:
hhwxw
2026-04-29 02:00:13 -07:00
committed by GitHub
parent 6c7b242181
commit d9270b8c6a
35 changed files with 5 additions and 5 deletions
+1 -1
View File
@@ -151,7 +151,7 @@ After tuning, configuration files will be generated:
- **Standard tuning**: `E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json`
- **Separate kernel tuning**: Two files for up/down kernels with TMA optimization flags
Move these files to `sglang/srt/layers/moe/fused_moe_triton/configs/triton_version/` directory to use them in SGLang.
Move these files to `sglang/srt/layers/moe/moe_runner/triton_utils/configs/triton_version/` directory to use them in SGLang.
### Supported Models
@@ -147,7 +147,7 @@ spec:
name: model
- mountPath: /dev/infiniband
name: ib
- mountPath: /sgl-workspace/sglang/python/sglang/srt/layers/moe/fused_moe_triton/configs
- mountPath: /sgl-workspace/sglang/python/sglang/srt/layers/moe/moe_runner/triton_utils/configs
name: cf
- mountPath: /root/.cache
name: sgl-cache
@@ -305,7 +305,7 @@ spec:
name: model
- mountPath: /dev/infiniband
name: ib
- mountPath: /sgl-workspace/sglang/python/sglang/srt/layers/moe/fused_moe_triton/configs
- mountPath: /sgl-workspace/sglang/python/sglang/srt/layers/moe/moe_runner/triton_utils/configs
name: cf
dnsPolicy: ClusterFirstWithHostNet
hostIPC: true
@@ -458,7 +458,7 @@ spec:
name: model
- mountPath: /dev/infiniband
name: ib
- mountPath: /sgl-workspace/sglang/python/sglang/srt/layers/moe/fused_moe_triton/configs
- mountPath: /sgl-workspace/sglang/python/sglang/srt/layers/moe/moe_runner/triton_utils/configs
name: cf
dnsPolicy: ClusterFirstWithHostNet
hostIPC: true
@@ -592,7 +592,7 @@ spec:
name: model
- mountPath: /dev/infiniband
name: ib
- mountPath: /sgl-workspace/sglang/python/sglang/srt/layers/moe/fused_moe_triton/configs
- mountPath: /sgl-workspace/sglang/python/sglang/srt/layers/moe/moe_runner/triton_utils/configs
name: cf
dnsPolicy: ClusterFirstWithHostNet
hostIPC: true