Merge tag 'v0.18.0' into v0.18.0-ori

3fb4b5fa · zhuwenwen · bcf25339 · 89138b21 · 3fb4b5fa · 3fb4b5fa
Commit 3fb4b5fa authored Mar 23, 2026 by zhuwenwen
20 changed files
--- a/tests/evals/gsm8k/configs/moe-refactor-dp-ep/Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor-dp-ep/Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor-dp-ep/Qwen3-30B-A3B-NvFp4-ModelOpt-fi-trtllm.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor-dp-ep/Qwen3-30B-A3B-NvFp4-ModelOpt-fi-trtllm.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-BF16-fi-cutlass.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-BF16-fi-cutlass.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-Fp8-ModelOpt-fi-cutlass.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-Fp8-ModelOpt-fi-cutlass.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-Fp8-ModelOpt-fi-trtllm.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-Fp8-ModelOpt-fi-trtllm.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-Fp8-ModelOpt-triton.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-Fp8-ModelOpt-triton.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Mixtral-8x7B-BF16-fi-cutlass.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Mixtral-8x7B-BF16-fi-cutlass.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Mixtral-8x7B-Fp8-AutoFp8-fi-cutlass.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Mixtral-8x7B-Fp8-AutoFp8-fi-cutlass.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Nemotron-Nano-30B-Fp8-ModelOpt-fi-trtllm.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Nemotron-Nano-30B-Fp8-ModelOpt-fi-trtllm.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Nemotron-Nano-30B-NvFp4-ModelOpt-fi-cutlass.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Nemotron-Nano-30B-NvFp4-ModelOpt-fi-cutlass.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-BF16-fi-cutlass.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-BF16-fi-cutlass.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-AutoFp8-fi-cutlass.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-AutoFp8-fi-cutlass.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-AutoFp8-fi-trtllm.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-AutoFp8-fi-trtllm.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-AutoFp8-triton.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-AutoFp8-triton.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-CT-Block-fi-cutlass.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-CT-Block-fi-cutlass.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-CT-Block-triton.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-CT-Block-triton.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-CT-fi-cutlass.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-CT-fi-cutlass.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-CT-fi-trtllm.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-CT-fi-trtllm.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-CT-vllm-cutlass.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-CT-vllm-cutlass.yaml
--- a/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass.yaml
+++ b/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass.yaml