Track simulator fidelity experiment artifacts
This commit is contained in:
@@ -0,0 +1,12 @@
|
||||
diff --git a/frontier/profiling/moe/moe_vllm_kernel.py b/frontier/profiling/moe/moe_vllm_kernel.py
|
||||
--- a/frontier/profiling/moe/moe_vllm_kernel.py
|
||||
+++ b/frontier/profiling/moe/moe_vllm_kernel.py
|
||||
@@ -232 +232 @@ def _invoke_kernel(
|
||||
- compute_type = tl.float16 # FP8 accumulates in FP16
|
||||
+ compute_type = tl.bfloat16
|
||||
@@ -510 +510,4 @@ def profile_vllm_fused_moe(
|
||||
- config_dtype = get_config_dtype_str(base_dtype)
|
||||
+ config_dtype = get_config_dtype_str(
|
||||
+ base_dtype,
|
||||
+ use_fp8_w8a8=use_fp8,
|
||||
+ )
|
||||
Reference in New Issue
Block a user