Enable optional FP32 compute for LM Head (#10729)

Thanks to MiniMax Team and Chenyang Zhao's support.
2025-09-29 20:45:17 -07:00
parent 8831c55c3d
commit d17986f8c6
6 changed files with 130 additions and 2 deletions
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -59,6 +59,7 @@ suites = {
        TestFile("quant/test_int8_kernel.py", 8),
        TestFile("quant/test_triton_scaled_mm.py", 8),
        TestFile("quant/test_w8a8_quantization.py", 46),
+        TestFile("rl/test_fp32_lm_head.py", 30),
        TestFile("rl/test_update_weights_from_disk.py", 114),
        TestFile("rl/test_update_weights_from_tensor.py", 48),
        TestFile("test_abort.py", 51),