EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Revert "[Perf][1/N] w8a8c8 support in dsv3.2/glm5 (#7029)" (#7288)

Browse Source 
### What this PR does / why we need it?
This reverts commit 7ed9e9de69, which
introduces an issue that the patch doesn't work with recompute scheduler
enabled.
- vLLM version: v0.17.0
- vLLM main:
4034c3d32e
---------
Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao
2026-03-15 20:19:09 +08:00
committed by GitHub
parent 29f195a91c
commit 0c299f79b9
24 changed files with 79 additions and 4281 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
csrc/build_aclnn.sh
View File

@@ -25,7 +25,7 @@ elif [[ "$SOC_VERSION" =~ ^ascend910b ]]; then
export CPATH=${ABSOLUTE_CATLASS_PATH}:${CPATH}
CUSTOM_OPS="moe_grouped_matmul;grouped_matmul_swiglu_quant_weight_nz_tensor_list;lightning_indexer_vllm;sparse_flash_attention;matmul_allreduce_add_rmsnorm;moe_init_routing_custom;moe_gating_top_k;add_rms_norm_bias;apply_top_k_top_p_custom;transpose_kv_cache_by_block;copy_and_expand_eagle_inputs;causal_conv1d;lightning_indexer_quant;"
CUSTOM_OPS="moe_grouped_matmul;grouped_matmul_swiglu_quant_weight_nz_tensor_list;lightning_indexer_vllm;sparse_flash_attention;matmul_allreduce_add_rmsnorm;moe_init_routing_custom;moe_gating_top_k;add_rms_norm_bias;apply_top_k_top_p_custom;transpose_kv_cache_by_block;copy_and_expand_eagle_inputs;causal_conv1d;"
SOC_ARG="ascend910b"
elif [[ "$SOC_VERSION" =~ ^ascend910_93 ]]; then
# ASCEND910C (A3) series
@@ -67,7 +67,6 @@ 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"