[ExecuTorch][WebGPU] Remove the orphan q4gsw_linear_coop4 shader

backends/webgpu/test/ops/test_quantized_linear.py

@@ -57,8 +57,8 @@ class Q4gswConfig:
     # decode GEMV: the handler routes M==1 -> bicol, so each reads its own per-
     # column scale (col0/col1) across many K-groups (down_proj: 256 groups). q4gsw
     # requires N % 8 == 0 (torchao pads N for the scale layout), so odd-N / N=1 are
-    # not exportable -- bicol's has1 odd-N guard is defensive (mirrors coop4's
-    # general-N robustness) and unreachable through this op.
+    # not exportable -- bicol's has1 odd-N guard is defensive and unreachable
+    # through this op.
     # M>1 prefill: prefer the steel GEMM (K%16==0) on a >=256-invocation device
     # (e.g. lvp); else shmem (K>=4096 or N>=2048) or register-tiled (SwiftShader
     # caps at 128). Same fp64 golden regardless of which kernel runs.

backends/webgpu/test/test_webgpu_native.cpp

@@ -284,8 +284,7 @@ const Q4gswConfig kQ4gswConfigs[] = {
     // The M==1 configs above (q/kv/gate/down_proj) exercise the bicol 2-col
     // decode GEMV (handler routes M==1 -> bicol; each reads its own per-column
     // scale over 64-256 K-groups). q4gsw requires N % 8 == 0, so odd-N is not
-    // exportable; bicol's has1 odd-N guard is defensive (mirrors coop4
-    // general-N robustness).
+    // exportable; bicol's has1 odd-N guard is defensive.
     // M>1: steel GEMM on a >=256-invocation device (K%16==0), else shmem/tiled.
     {"steel", 96, 2048, 256, 1e-4f, 1e-3f, true, false}, // steel-isolating
     // Same shape as "steel" run under the f16-multiply steel kernel; the f16