[bugfix] restore pr-7029 and fix patch error (#7294)
### What this PR does / why we need it?
This PR restores #7029, which adds W8A8C8 support for dsv3.2/glm5 using
the `lightning_indexer_quant` ops in the pd-mix stage.
The original PR was reverted by #7288 because the patch did not work
with the recompute scheduler.
This PR also fixes the patching issue so that it works correctly with
the recompute scheduler.
### Does this PR introduce _any_ user-facing change?
Yes. To enable LI C8, users need to set the `enable_sparse_c8` option to
`"true"` in `additional_config`.
- vLLM version: v0.17.0
- vLLM main:
4034c3d32e
---------
Signed-off-by: rjg-lyh <1318825571@qq.com>
This commit is contained in:
@@ -25,7 +25,7 @@ elif [[ "$SOC_VERSION" =~ ^ascend910b ]]; then
|
||||
export CPATH=${ABSOLUTE_CATLASS_PATH}:${CPATH}
|
||||
|
||||
|
||||
CUSTOM_OPS="moe_grouped_matmul;grouped_matmul_swiglu_quant_weight_nz_tensor_list;lightning_indexer_vllm;sparse_flash_attention;matmul_allreduce_add_rmsnorm;moe_init_routing_custom;moe_gating_top_k;add_rms_norm_bias;apply_top_k_top_p_custom;transpose_kv_cache_by_block;copy_and_expand_eagle_inputs;causal_conv1d;"
|
||||
CUSTOM_OPS="moe_grouped_matmul;grouped_matmul_swiglu_quant_weight_nz_tensor_list;lightning_indexer_vllm;sparse_flash_attention;matmul_allreduce_add_rmsnorm;moe_init_routing_custom;moe_gating_top_k;add_rms_norm_bias;apply_top_k_top_p_custom;transpose_kv_cache_by_block;copy_and_expand_eagle_inputs;causal_conv1d;lightning_indexer_quant;"
|
||||
SOC_ARG="ascend910b"
|
||||
elif [[ "$SOC_VERSION" =~ ^ascend910_93 ]]; then
|
||||
# ASCEND910C (A3) series
|
||||
@@ -67,6 +67,7 @@ elif [[ "$SOC_VERSION" =~ ^ascend910_93 ]]; then
|
||||
"copy_and_expand_eagle_inputs"
|
||||
"causal_conv1d"
|
||||
"moe_grouped_matmul"
|
||||
"lightning_indexer_quant"
|
||||
)
|
||||
CUSTOM_OPS=$(IFS=';'; echo "${CUSTOM_OPS_ARRAY[*]}")
|
||||
SOC_ARG="ascend910_93"
|
||||
|
||||
Reference in New Issue
Block a user