df1ee8070d
### What this PR does / why we need it?
Implement a unified parallelized speculative decoding in VLLM
Ascend，which can simultaneously support parallel speculative inference
schemes such as Pard, P-Eagle, etc. refer to
https://github.com/vllm-project/vllm-ascend/pull/6565 and
https://github.com/vllm-project/vllm-ascend/pull/4078
### How was this patch tested?
run with parallel drafting script:
export target=/model/Llama-3.1-8B-Instruct
export draft=/model/PARD-Llama-3.2-1B
export CUDA_VISIBLE_DEVICES=6
export ASCEND_RT_VISIBLE_DEVICES=6
vllm serve $target \
--tensor-parallel-size 1 \
--max-model-len 4096 \
--no-enable-prefix-caching \
--port 8811 \
--speculative-config '{"model": "/model/PARD-Llama-3.2-1B", "method":
"draft_model", "num_speculative_tokens": 8, "parallel_drafting": true}'
base script:
export target=/model/Llama-3.1-8B-Instruct
export draft=/model/PARD-Llama-3.2-1B
export CUDA_VISIBLE_DEVICES=6
export ASCEND_RT_VISIBLE_DEVICES=6
vllm serve $target \
--tensor-parallel-size 1 \
--max-model-len 4096 \
--no-enable-prefix-caching \
--port 8811
benchmark script:
MAX_CONCURRENCY=1
NUM_PROMPTS=80
vllm bench serve --port 8811 \
--temperature 0 \
--model /model/Llama-3.1-8B-Instruct \
--backend openai-chat \
--endpoint /v1/chat/completions \
--dataset-name hf \
--dataset-path philschmid/mt-bench \
--num-prompts ${NUM_PROMPTS} \
--max-concurrency ${MAX_CONCURRENCY} \
--seed 1234
test results :
base(without spec decode): TTFT 79.46ms TPOT 26.99ms
output_tokens_throughput 36.75 tok/s
this pr(with parallel drafting): TTFT 72.24ms TPOT 13.45ms
output_tokens_throughput 72.98 tok/s
per-position acceptance(from position 0 to 7):
79.48%、56.93%、40%、27.90%、19.79%、14.25%、10.57%、7.61%.
----------------------------------------------------------------------
run on qwen3 model script ：
export target=/model/Qwen3-1.7B
export draft=/model/PARD-Qwen3-0.6B
export CUDA_VISIBLE_DEVICES=1
export ASCEND_RT_VISIBLE_DEVICES=1
vllm serve $target \
--tensor-parallel-size 1 \
--max-model-len 4096 \
--no-enable-prefix-caching \
--port 8811 \
--speculative-config '{"model": "/model/PARD-Qwen3-0.6B", "method":
"draft_model", "num_speculative_tokens": 8, "parallel_drafting": true}'
cc @NickJudyHvv
- vLLM version: v0.15.0
- vLLM main:
9562912cea
---------
Signed-off-by: 01267596 <xiongkai123@cmbchina.com>
Signed-off-by: kx <1670186653@qq.com>
Signed-off-by: HF-001 <1670186653@qq.com>
Co-authored-by: 01267596 <xiongkai123@cmbchina.com>
88 lines
3.0 KiB
Bash
88 lines
3.0 KiB
Bash
#!/bin/bash
|
|
|
|
ROOT_DIR=$1
|
|
SOC_VERSION=$2
|
|
|
|
if [[ "$SOC_VERSION" =~ ^ascend310 ]]; then
|
|
# ASCEND310P series
|
|
# currently, no custom aclnn ops for ASCEND310 series
|
|
# CUSTOM_OPS=""
|
|
# SOC_ARG="ascend310p"
|
|
exit 0
|
|
elif [[ "$SOC_VERSION" =~ ^ascend910b ]]; then
|
|
# ASCEND910B (A2) series
|
|
# dependency: catlass
|
|
git config --global --add safe.directory "$ROOT_DIR"
|
|
CATLASS_PATH=${ROOT_DIR}/csrc/third_party/catlass/include
|
|
if [[ ! -d "${CATLASS_PATH}" ]]; then
|
|
echo "dependency catlass is missing, try to fetch it..."
|
|
if ! git submodule update --init --recursive; then
|
|
echo "fetch failed"
|
|
exit 1
|
|
fi
|
|
fi
|
|
ABSOLUTE_CATLASS_PATH=$(cd "${CATLASS_PATH}" && pwd)
|
|
export CPATH=${ABSOLUTE_CATLASS_PATH}:${CPATH}
|
|
|
|
|
|
CUSTOM_OPS="moe_grouped_matmul;grouped_matmul_swiglu_quant_weight_nz_tensor_list;lightning_indexer_vllm;sparse_flash_attention;matmul_allreduce_add_rmsnorm;moe_init_routing_custom;moe_gating_top_k;add_rms_norm_bias;apply_top_k_top_p_custom;transpose_kv_cache_by_block;copy_and_expand_eagle_inputs;causal_conv1d;"
|
|
SOC_ARG="ascend910b"
|
|
elif [[ "$SOC_VERSION" =~ ^ascend910_93 ]]; then
|
|
# ASCEND910C (A3) series
|
|
# dependency: catlass
|
|
git config --global --add safe.directory "$ROOT_DIR"
|
|
CATLASS_PATH=${ROOT_DIR}/csrc/third_party/catlass/include
|
|
if [[ ! -d "${CATLASS_PATH}" ]]; then
|
|
echo "dependency catlass is missing, try to fetch it..."
|
|
if ! git submodule update --init --recursive; then
|
|
echo "fetch failed"
|
|
exit 1
|
|
fi
|
|
fi
|
|
# dependency: cann-toolkit file moe_distribute_base.h
|
|
HCCL_STRUCT_FILE_PATH=$(find -L "${ASCEND_TOOLKIT_HOME}" -name "moe_distribute_base.h" 2>/dev/null | head -n1)
|
|
if [ -z "$HCCL_STRUCT_FILE_PATH" ]; then
|
|
echo "cannot find moe_distribute_base.h file in CANN env"
|
|
exit 1
|
|
fi
|
|
# for dispatch_gmm_combine_decode
|
|
yes | cp "${HCCL_STRUCT_FILE_PATH}" "${ROOT_DIR}/csrc/utils/inc/kernel"
|
|
|
|
CUSTOM_OPS_ARRAY=(
|
|
"grouped_matmul_swiglu_quant_weight_nz_tensor_list"
|
|
"lightning_indexer_vllm"
|
|
"sparse_flash_attention"
|
|
"dispatch_ffn_combine"
|
|
"dispatch_ffn_combine_bf16"
|
|
"dispatch_gmm_combine_decode"
|
|
"moe_combine_normal"
|
|
"moe_dispatch_normal"
|
|
"dispatch_layout"
|
|
"notify_dispatch"
|
|
"moe_init_routing_custom"
|
|
"moe_gating_top_k"
|
|
"add_rms_norm_bias"
|
|
"apply_top_k_top_p_custom"
|
|
"transpose_kv_cache_by_block"
|
|
"copy_and_expand_eagle_inputs"
|
|
"causal_conv1d"
|
|
"moe_grouped_matmul"
|
|
)
|
|
CUSTOM_OPS=$(IFS=';'; echo "${CUSTOM_OPS_ARRAY[*]}")
|
|
SOC_ARG="ascend910_93"
|
|
else
|
|
# others
|
|
# currently, no custom aclnn ops for other series
|
|
exit 0
|
|
fi
|
|
|
|
|
|
# build custom ops
|
|
cd csrc
|
|
rm -rf build output
|
|
echo "building custom ops $CUSTOM_OPS for $SOC_VERSION"
|
|
bash build.sh -n "$CUSTOM_OPS" -c "$SOC_ARG"
|
|
|
|
# install custom ops to vllm_ascend/_cann_ops_custom
|
|
./output/CANN-custom_ops*.run --install-path=$ROOT_DIR/vllm_ascend/_cann_ops_custom
|