Enabling some B200-specific tests on MI355 (#35253)
Signed-off-by: Alexei V. Ivanov <alexei.ivanov@amd.com> Signed-off-by: Alexei-V-Ivanov-AMD <156011006+Alexei-V-Ivanov-AMD@users.noreply.github.com>
This commit is contained in:
Alexei-V-Ivanov-AMD
committed by
GitHub
GitHub
parent
f3c6c9c9d7
commit
225d1090a0
@@ -499,17 +499,6 @@ steps:
|
||||
- pytest -v -s v1/determinism/test_batch_invariance.py
|
||||
- pytest -v -s v1/determinism/test_rms_norm_batch_invariant.py
|
||||
|
||||
- label: V1 Test attention (B200) # 10min
|
||||
timeout_in_minutes: 30
|
||||
gpu: b200
|
||||
source_file_dependencies:
|
||||
- vllm/config/attention.py
|
||||
- vllm/model_executor/layers/attention
|
||||
- vllm/v1/attention
|
||||
- tests/v1/attention
|
||||
commands:
|
||||
- pytest -v -s v1/attention
|
||||
|
||||
- label: V1 Test others (CPU) # 5 mins
|
||||
mirror_hardwares: [amdexperimental, amdproduction, amdtentative]
|
||||
agent_pool: mi325_1
|
||||
@@ -1185,47 +1174,40 @@ steps:
|
||||
# Whisper needs spawn method to avoid deadlock
|
||||
- VLLM_WORKER_MULTIPROC_METHOD=spawn python3 examples/offline_inference/audio_language.py --model-type whisper
|
||||
|
||||
- label: Blackwell Test # 21 min
|
||||
timeout_in_minutes: 30
|
||||
- label: Blackwell Fusion and Compile Tests # 30 min
|
||||
timeout_in_minutes: 40
|
||||
working_dir: "/vllm-workspace/"
|
||||
gpu: b200
|
||||
# optional: true
|
||||
source_file_dependencies:
|
||||
- csrc/quantization/fp4/
|
||||
- csrc/attention/mla/
|
||||
- csrc/quantization/cutlass_w8a8/moe/
|
||||
- vllm/model_executor/layers/fused_moe/cutlass_moe.py
|
||||
- vllm/model_executor/layers/fused_moe/flashinfer_cutlass_moe.py
|
||||
- vllm/model_executor/layers/fused_moe/flashinfer_a2a_prepare_finalize.py
|
||||
- vllm/model_executor/layers/quantization/utils/flashinfer_utils.py
|
||||
- vllm/v1/attention/backends/flashinfer.py
|
||||
- vllm/v1/attention/backends/mla/cutlass_mla.py
|
||||
- vllm/v1/attention/backends/mla/flashinfer_mla.py
|
||||
- vllm/v1/attention/selector.py
|
||||
- vllm/platforms/cuda.py
|
||||
- vllm/v1/worker/
|
||||
- vllm/v1/cudagraph_dispatcher.py
|
||||
- vllm/compilation/
|
||||
# can affect pattern matching
|
||||
- vllm/model_executor/layers/layernorm.py
|
||||
- vllm/model_executor/layers/activation.py
|
||||
- vllm/model_executor/layers/quantization/input_quant_fp8.py
|
||||
- tests/compile/passes/test_fusion_attn.py
|
||||
- tests/compile/passes/test_silu_mul_quant_fusion.py
|
||||
- tests/compile/passes/distributed/test_fusion_all_reduce.py
|
||||
- tests/compile/fullgraph/test_full_graph.py
|
||||
commands:
|
||||
- nvidia-smi
|
||||
- python3 examples/offline_inference/basic/chat.py
|
||||
# Attention
|
||||
# num_heads2 broken by https://github.com/flashinfer-ai/flashinfer/issues/1353
|
||||
- pytest -v -s tests/kernels/attention/test_attention_selector.py
|
||||
- pytest -v -s tests/kernels/attention/test_flashinfer.py -k 'not num_heads2'
|
||||
- pytest -v -s tests/kernels/attention/test_flashinfer_trtllm_attention.py
|
||||
- pytest -v -s tests/kernels/attention/test_cutlass_mla_decode.py
|
||||
- pytest -v -s tests/kernels/attention/test_flashinfer_mla_decode.py
|
||||
# Quantization
|
||||
- pytest -v -s tests/kernels/quantization/test_cutlass_scaled_mm.py -k 'fp8'
|
||||
- pytest -v -s tests/kernels/quantization/test_nvfp4_quant.py
|
||||
- pytest -v -s tests/kernels/quantization/test_silu_mul_nvfp4_quant.py
|
||||
- pytest -v -s tests/kernels/quantization/test_nvfp4_scaled_mm.py
|
||||
- pytest -v -s tests/kernels/quantization/test_flashinfer_scaled_mm.py
|
||||
- pytest -v -s tests/kernels/quantization/test_flashinfer_nvfp4_scaled_mm.py
|
||||
- pytest -v -s tests/kernels/quantization/test_nvfp4_qutlass.py
|
||||
- pytest -v -s tests/kernels/quantization/test_mxfp4_qutlass.py
|
||||
- pytest -v -s tests/kernels/moe/test_nvfp4_moe.py
|
||||
- pytest -v -s tests/kernels/moe/test_ocp_mx_moe.py
|
||||
- pytest -v -s tests/kernels/moe/test_flashinfer.py
|
||||
- pytest -v -s tests/kernels/moe/test_cutedsl_moe.py
|
||||
- pytest -v -s tests/compile/passes/test_fusion_attn.py
|
||||
- pytest -v -s tests/compile/passes/test_silu_mul_quant_fusion.py
|
||||
# this runner has 2 GPUs available even though num_gpus=2 is not set
|
||||
- pytest -v -s tests/compile/passes/distributed/test_fusion_all_reduce.py
|
||||
|
||||
# # Limit to Inductor partition, no custom ops, and allreduce & attn fusion to reduce running time
|
||||
# # Wrap with quotes to escape yaml
|
||||
# - "pytest -v -s tests/compile/distributed/test_fusions_e2e.py::test_tp2_attn_quant_allreduce_rmsnorm -k 'True and not +quant_fp8 and not +rms_norm'"
|
||||
# Old E2E tests were removed in https://github.com/vllm-project/vllm/pull/33293
|
||||
# in favor of new tests in fusions_e2e. We avoid replicating the new jobs in this file as it's deprecated.
|
||||
|
||||
# test_fp8_kv_scale_compile requires FlashAttention (not supported on default L4/L40)
|
||||
- pytest -v -s tests/compile/fullgraph/test_full_graph.py::test_fp8_kv_scale_compile
|
||||
|
||||
- label: Blackwell GPT-OSS Eval
|
||||
timeout_in_minutes: 60
|
||||
@@ -1258,16 +1240,6 @@ steps:
|
||||
commands:
|
||||
- pytest -s -v tests/quantization/test_blackwell_moe.py
|
||||
|
||||
- label: Blackwell LM Eval Small Models
|
||||
timeout_in_minutes: 120
|
||||
gpu: b200
|
||||
optional: true # run on nightlies
|
||||
source_file_dependencies:
|
||||
- csrc/
|
||||
- vllm/model_executor/layers/quantization
|
||||
commands:
|
||||
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt
|
||||
|
||||
##### 1 GPU test #####
|
||||
##### multi gpus test #####
|
||||
|
||||
@@ -1681,16 +1653,6 @@ steps:
|
||||
commands:
|
||||
- bash .buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_block_ep_eplb.sh 0.8 200 8020
|
||||
|
||||
- label: Qwen3-30B-A3B-FP8-block Accuracy (B200)
|
||||
timeout_in_minutes: 60
|
||||
gpu: b200
|
||||
optional: true
|
||||
num_gpus: 2
|
||||
working_dir: "/vllm-workspace"
|
||||
commands:
|
||||
- bash .buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_block_ep_eplb.sh 0.8 200 8020 2 1
|
||||
|
||||
|
||||
- label: Qwen3-Next-80B-A3B-Instruct MTP Async EPLB Accuracy
|
||||
timeout_in_minutes: 60
|
||||
mirror_hardwares: [amdexperimental, amdproduction]
|
||||
@@ -2176,19 +2138,6 @@ steps:
|
||||
|
||||
# TODO: Add the "V1 Test attention (MI300)" test group
|
||||
|
||||
- label: V1 Test attention (H100) # 10min
|
||||
mirror_hardwares: [amdexperimental]
|
||||
agent_pool: mi355_1
|
||||
timeout_in_minutes: 30
|
||||
gpu: h100
|
||||
source_file_dependencies:
|
||||
- vllm/config/attention.py
|
||||
- vllm/model_executor/layers/attention
|
||||
- vllm/v1/attention
|
||||
- tests/v1/attention
|
||||
commands:
|
||||
- pytest -v -s v1/attention
|
||||
|
||||
- label: Batch Invariance Tests (H100) # 10min
|
||||
mirror_hardwares: [amdexperimental]
|
||||
agent_pool: mi355_1
|
||||
@@ -2205,6 +2154,8 @@ steps:
|
||||
- pytest -v -s v1/determinism/test_rms_norm_batch_invariant.py
|
||||
|
||||
- label: V1 Test attention (B200) # 10min
|
||||
mirror_hardwares: [amdexperimental, amdmi355]
|
||||
agent_pool: mi355_1
|
||||
timeout_in_minutes: 30
|
||||
gpu: b200
|
||||
source_file_dependencies:
|
||||
@@ -2829,7 +2780,9 @@ steps:
|
||||
# Whisper needs spawn method to avoid deadlock
|
||||
- VLLM_WORKER_MULTIPROC_METHOD=spawn python3 examples/offline_inference/audio_language.py --model-type whisper
|
||||
|
||||
- label: Blackwell Test # 21 min
|
||||
- label: Blackwell Test (MI355) # 21 min
|
||||
mirror_hardwares: [amdexperimental, amdmi355]
|
||||
agent_pool: mi355_1
|
||||
timeout_in_minutes: 30
|
||||
working_dir: "/vllm-workspace/"
|
||||
gpu: b200
|
||||
@@ -2848,28 +2801,28 @@ steps:
|
||||
- vllm/v1/attention/selector.py
|
||||
- vllm/platforms/cuda.py
|
||||
commands:
|
||||
- nvidia-smi
|
||||
rocm-smi
|
||||
- python3 examples/offline_inference/basic/chat.py
|
||||
# Attention
|
||||
# num_heads2 broken by https://github.com/flashinfer-ai/flashinfer/issues/1353
|
||||
- pytest -v -s tests/kernels/attention/test_attention_selector.py
|
||||
- pytest -v -s tests/kernels/attention/test_flashinfer.py -k 'not num_heads2'
|
||||
- pytest -v -s tests/kernels/attention/test_flashinfer_trtllm_attention.py
|
||||
- pytest -v -s tests/kernels/attention/test_cutlass_mla_decode.py
|
||||
- pytest -v -s tests/kernels/attention/test_flashinfer_mla_decode.py
|
||||
# Quantization
|
||||
- pytest -v -s tests/kernels/quantization/test_cutlass_scaled_mm.py -k 'fp8'
|
||||
- pytest -v -s tests/kernels/quantization/test_nvfp4_quant.py
|
||||
- pytest -v -s tests/kernels/quantization/test_silu_mul_nvfp4_quant.py
|
||||
- pytest -v -s tests/kernels/quantization/test_nvfp4_scaled_mm.py
|
||||
- pytest -v -s tests/kernels/quantization/test_flashinfer_scaled_mm.py
|
||||
- pytest -v -s tests/kernels/quantization/test_flashinfer_nvfp4_scaled_mm.py
|
||||
- pytest -v -s tests/kernels/quantization/test_nvfp4_qutlass.py
|
||||
- pytest -v -s tests/kernels/quantization/test_mxfp4_qutlass.py
|
||||
- pytest -v -s tests/kernels/moe/test_nvfp4_moe.py
|
||||
- pytest -v -s tests/kernels/moe/test_ocp_mx_moe.py
|
||||
- pytest -v -s tests/kernels/moe/test_flashinfer.py
|
||||
- pytest -v -s tests/kernels/moe/test_cutedsl_moe.py
|
||||
- pytest -v -s tests/kernels/attention/test_attention_selector.py
|
||||
#- pytest -v -s tests/kernels/attention/test_flashinfer.py -k 'not num_heads2'
|
||||
#- pytest -v -s tests/kernels/attention/test_flashinfer_trtllm_attention.py
|
||||
#- pytest -v -s tests/kernels/attention/test_cutlass_mla_decode.py
|
||||
#- pytest -v -s tests/kernels/attention/test_flashinfer_mla_decode.py
|
||||
## Quantization
|
||||
#- pytest -v -s tests/kernels/quantization/test_cutlass_scaled_mm.py -k 'fp8'
|
||||
#- pytest -v -s tests/kernels/quantization/test_nvfp4_quant.py
|
||||
#- pytest -v -s tests/kernels/quantization/test_silu_mul_nvfp4_quant.py
|
||||
#- pytest -v -s tests/kernels/quantization/test_nvfp4_scaled_mm.py
|
||||
#- pytest -v -s tests/kernels/quantization/test_flashinfer_scaled_mm.py
|
||||
#- pytest -v -s tests/kernels/quantization/test_flashinfer_nvfp4_scaled_mm.py
|
||||
#- pytest -v -s tests/kernels/quantization/test_nvfp4_qutlass.py
|
||||
#- pytest -v -s tests/kernels/quantization/test_mxfp4_qutlass.py
|
||||
#- pytest -v -s tests/kernels/moe/test_nvfp4_moe.py
|
||||
#- pytest -v -s tests/kernels/moe/test_ocp_mx_moe.py
|
||||
#- pytest -v -s tests/kernels/moe/test_flashinfer.py
|
||||
#- pytest -v -s tests/kernels/moe/test_cutedsl_moe.py
|
||||
|
||||
- label: Blackwell Fusion and Compile Tests # 30 min
|
||||
timeout_in_minutes: 40
|
||||
@@ -2939,13 +2892,15 @@ steps:
|
||||
|
||||
- label: Blackwell LM Eval Small Models
|
||||
timeout_in_minutes: 120
|
||||
mirror_hardwares: [amdexperimental, amdproduction, amdmi355]
|
||||
agent_pool: mi355_2
|
||||
gpu: b200
|
||||
optional: true # run on nightlies
|
||||
source_file_dependencies:
|
||||
- csrc/
|
||||
- vllm/model_executor/layers/quantization
|
||||
commands:
|
||||
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt
|
||||
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-mi355.txt
|
||||
|
||||
##### 1 GPU test #####
|
||||
##### multi gpus test #####
|
||||
@@ -3328,18 +3283,9 @@ steps:
|
||||
commands:
|
||||
- bash .buildkite/scripts/scheduled_integration_test/deepseek_v2_lite_ep_eplb.sh 0.25 200 8010
|
||||
|
||||
- label: Qwen3-30B-A3B-FP8-block Accuracy (H100)
|
||||
mirror_hardwares: [amdexperimental, amdproduction]
|
||||
agent_pool: mi355_4
|
||||
timeout_in_minutes: 60
|
||||
gpu: h100
|
||||
optional: true
|
||||
num_gpus: 4
|
||||
working_dir: "/vllm-workspace"
|
||||
commands:
|
||||
- bash .buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_block_ep_eplb.sh 0.8 200 8020
|
||||
|
||||
- label: Qwen3-30B-A3B-FP8-block Accuracy (B200)
|
||||
- label: Qwen3-30B-A3B-FP8-block Accuracy (B200/MI355)
|
||||
mirror_hardwares: [amdexperimental, amdproduction, amdmi355]
|
||||
agent_pool: mi355_2
|
||||
timeout_in_minutes: 60
|
||||
gpu: b200
|
||||
optional: true
|
||||
@@ -3358,3 +3304,18 @@ steps:
|
||||
working_dir: "/vllm-workspace"
|
||||
commands:
|
||||
- bash .buildkite/scripts/scheduled_integration_test/qwen3_next_mtp_async_eplb.sh 0.8 1319 8040
|
||||
|
||||
- label: Attention Benchmarks Smoke Test (B200/MI355)
|
||||
device: b200
|
||||
mirror_hardwares: [amdexperimental, amdmi355]
|
||||
agent_pool: mi355_2
|
||||
num_gpus: 2
|
||||
optional: true
|
||||
working_dir: "/vllm-workspace/"
|
||||
timeout_in_minutes: 10
|
||||
source_file_dependencies:
|
||||
- benchmarks/attention_benchmarks/
|
||||
- vllm/v1/attention/
|
||||
commands:
|
||||
- python3 benchmarks/attention_benchmarks/benchmark.py --backends ROCM_ATTN ROCM_AITER_FA ROCM_AITER_UNIFIED_ATTN --batch-specs "8q1s1k" --repeats 1 --warmup-iters 1
|
||||
|
||||
|
||||
Reference in New Issue
Block a user