diff --git a/.github/workflows/release_whl.yml b/.github/workflows/release_whl.yml index bf1f62f..351ea42 100644 --- a/.github/workflows/release_whl.yml +++ b/.github/workflows/release_whl.yml @@ -57,7 +57,13 @@ jobs: - name: Print run: | lscpu - + + - name: Free up disk space + uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1 + with: + tool-cache: true + docker-images: false + - name: Build wheel run: | ls diff --git a/vllm_ascend/quantization/quant_config.py b/vllm_ascend/quantization/quant_config.py index e742852..d31a696 100644 --- a/vllm_ascend/quantization/quant_config.py +++ b/vllm_ascend/quantization/quant_config.py @@ -193,6 +193,11 @@ packed_modules_model_mapping = { ["experts.0.gate_proj", "experts.0.up_proj", "experts.0.down_proj"], "fused_qkv_a_proj": ["q_a_proj", "kv_a_proj_with_mqa"] }, + "kimi_k2": { + "gate_up_proj": ["gate_proj", "up_proj"], + "experts": + ["experts.0.gate_proj", "experts.0.up_proj", "experts.0.down_proj"] + }, "deepseek_v32": { "gate_up_proj": ["gate_proj", "up_proj"], "experts":