|
|
|
@@ -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
|
|
|
|
|