[CI] Shard MoE refactor B200 eval (#52327)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
This commit is contained in:
@@ -0,0 +1,3 @@
|
||||
DeepSeek-V4-Flash-deepgemm-mega-moe.yaml
|
||||
Qwen3-30B-A3B-NvFp4-ModelOpt-marlin.yaml
|
||||
Qwen3-30B-A3B-NvFp4-ModelOpt-fi-trtllm.yaml
|
||||
@@ -0,0 +1,5 @@
|
||||
Nemotron-Nano-30B-Fp8-ModelOpt-fi-trtllm.yaml
|
||||
Nemotron-Nano-30B-NvFp4-ModelOpt-fi-cutlass.yaml
|
||||
Llama-4-Scout-Fp8-CT-vllm-cutlass.yaml
|
||||
Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass.yaml
|
||||
Qwen3-30B-A3B-NvFp4-CT-fi-cutlass.yaml
|
||||
@@ -0,0 +1,5 @@
|
||||
Llama-4-Scout-Fp8-ModelOpt-fi-trtllm.yaml
|
||||
Qwen3-30B-A3B-NvFp4-CT-fi-trtllm.yaml
|
||||
Qwen3-30B-A3B-NvFp4-CT-vllm-cutlass.yaml
|
||||
Llama-4-Scout-BF16-triton.yaml
|
||||
Qwen3-30B-A3B-NvFp4-ModelOpt-vllm-cutlass.yaml
|
||||
@@ -0,0 +1,6 @@
|
||||
Llama-4-Scout-BF16-fi-cutlass.yaml
|
||||
Qwen3-30B-A3B-Fp8-AutoFp8-fi-trtllm.yaml
|
||||
Nemotron-Nano-30B-NvFp4-ModelOpt-vllm-cutlass.yaml
|
||||
Mixtral-8x7B-BF16-fi-cutlass.yaml
|
||||
Qwen3-30B-A3B-NvFp4-CT-marlin.yaml
|
||||
Mixtral-8x7B-BF16-triton.yaml
|
||||
Reference in New Issue
Block a user