[CI] Shard Humming H100 eval (#52326)

Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>

.buildkite/test_areas/lm_eval.yaml

@@ -225,12 +225,13 @@ steps:
   commands:
   - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/humming/config-act-int8.txt
 
-- label: LM Eval Humming f16 (H100 - TEMPORARY)
+- label: LM Eval Humming f16 (H100 - TEMPORARY) %N
   key: lm-eval-humming-f16-h100
   timeout_in_minutes: 70
   device: h100
   optional: true
   num_devices: 1
+  parallelism: 3
   source_file_dependencies:
   - vllm/model_executor/layers/quantization/humming.py
   - vllm/model_executor/layers/quantization/utils/humming_utils.py
@@ -238,7 +239,7 @@ steps:
   - vllm/model_executor/layers/fused_moe/oracle/
   - vllm/model_executor/kernels/linear/
   commands:
-  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/humming/config.txt
+  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/humming/config-h100-shard-$$BUILDKITE_PARALLEL_JOB.txt
 
 - label: LM Eval Humming Act fp8/int8 (H100 - TEMPORARY)
   key: lm-eval-humming-act-h100

tests/evals/gsm8k/configs/humming/config-h100-shard-0.txt

@@ -0,0 +1,5 @@
+Qwen3.5-35B-A3B-experts-int8-humming.yaml
+Qwen3-30B-A3B-Instruct-2507-quantized.w8a8-humming.yaml
+Qwen3-30B-A3B-Fp8-v1-humming.yaml
+Qwen3-30B-A3B-NVFP4-humming.yaml
+Qwen2-1.5B-Instruct-FP8W8-humming.yaml

tests/evals/gsm8k/configs/humming/config-h100-shard-1.txt

@@ -0,0 +1,5 @@
+Qwen3.6-35B-A3B-NVFP4-humming.yaml
+Qwen3-30B-A3B-AWQ-humming.yaml
+Qwen3-30B-A3B-GPTQ-Int4-humming.yaml
+Qwen3-30B-A3B-FP8-block-humming.yaml
+Qwen3-0.6B-MXFP8-humming.yaml

tests/evals/gsm8k/configs/humming/config-h100-shard-2.txt

@@ -0,0 +1,4 @@
+NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4-humming.yaml
+Qwen3.5-35B-A3B-FP8-humming.yaml
+Qwen3-30B-A3B-MXFP4A16-humming.yaml
+gpt-oss-20b-humming.yaml