[CI] Split LM Eval TurboQuant KV Cache into per-config jobs (#57113)

Signed-off-by: Thang Nguyen <thangnguyenvn647@gmail.com>
Co-authored-by: Kimi <noreply@moonshot.ai>
This commit is contained in:
Thang Nguyen
2026-09-22 14:49:06 -07:00
committed by GitHub
co-authored by Kimi
parent 5c3b61e9c4
commit 4ec0b95c44
6 changed files with 44 additions and 8 deletions
+40 -4
View File
@@ -587,9 +587,9 @@ steps:
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/humming/config-act-fp8.txt
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/humming/config-act-int8.txt
- label: ":nvidia: (H200 MIG 18GB) LM Eval TurboQuant KV Cache"
key: lm-eval-turboquant-kv-cache
timeout_in_minutes: 55
- label: ":nvidia: (H200 MIG 18GB) LM Eval TurboQuant k8v4"
key: lm-eval-turboquant-k8v4
timeout_in_minutes: 30
device: h200_18gb
source_file_dependencies:
- vllm/model_executor/layers/quantization/turboquant/
@@ -597,7 +597,43 @@ steps:
- vllm/v1/attention/ops/triton_turboquant_decode.py
- vllm/v1/attention/ops/triton_turboquant_store.py
commands:
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/models-turboquant.txt
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/models-turboquant-k8v4.txt
- label: ":nvidia: (H200 MIG 18GB) LM Eval TurboQuant t4nc"
key: lm-eval-turboquant-t4nc
timeout_in_minutes: 30
device: h200_18gb
source_file_dependencies:
- vllm/model_executor/layers/quantization/turboquant/
- vllm/v1/attention/backends/turboquant_attn.py
- vllm/v1/attention/ops/triton_turboquant_decode.py
- vllm/v1/attention/ops/triton_turboquant_store.py
commands:
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/models-turboquant-t4nc.txt
- label: ":nvidia: (H200 MIG 18GB) LM Eval TurboQuant k3v4nc"
key: lm-eval-turboquant-k3v4nc
timeout_in_minutes: 30
device: h200_18gb
source_file_dependencies:
- vllm/model_executor/layers/quantization/turboquant/
- vllm/v1/attention/backends/turboquant_attn.py
- vllm/v1/attention/ops/triton_turboquant_decode.py
- vllm/v1/attention/ops/triton_turboquant_store.py
commands:
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/models-turboquant-k3v4nc.txt
- label: ":nvidia: (H200 MIG 18GB) LM Eval TurboQuant t3nc"
key: lm-eval-turboquant-t3nc
timeout_in_minutes: 30
device: h200_18gb
source_file_dependencies:
- vllm/model_executor/layers/quantization/turboquant/
- vllm/v1/attention/backends/turboquant_attn.py
- vllm/v1/attention/ops/triton_turboquant_decode.py
- vllm/v1/attention/ops/triton_turboquant_store.py
commands:
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/models-turboquant-t3nc.txt
- label: ":nvidia: (H100) GPQA Eval (GPT-OSS)"
key: gpqa-eval-gpt-oss-2xh100
@@ -0,0 +1 @@
Qwen3-4B-TQ-k3v4nc.yaml
@@ -0,0 +1 @@
Qwen3-4B-TQ-k8v4.yaml
@@ -0,0 +1 @@
Qwen3-4B-TQ-t3nc.yaml
@@ -0,0 +1 @@
Qwen3-4B-TQ-t4nc.yaml
@@ -1,4 +0,0 @@
Qwen3-4B-TQ-k8v4.yaml
Qwen3-4B-TQ-t4nc.yaml
Qwen3-4B-TQ-k3v4nc.yaml
Qwen3-4B-TQ-t3nc.yaml