apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 17:11:21 +08:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

supports dynamic Cfp8 (#3767)
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* supports dynamic Cfp8

* add unittest
This commit is contained in:
lzy
2025-09-08 11:41:29 +08:00
committed by GitHub
parent b5e20e3015
commit af49b81ffd
20 changed files with 1417 additions and 225 deletions
Download Patch File Download Diff File Expand all files Collapse all files
custom_ops/gpu_ops/append_attn/template_instantiation/append_attention_c8_bfloat16_bfloat16_kernel.cu
+2
View File
@@ -56,6 +56,7 @@ CascadeAppendAttentionC8Kernel<paddle::bfloat16, paddle::bfloat16, false>(
const bool causal,
const bool is_decoder,
const bool enable_prefill,
const std::string& cache_quant_type_str,
cudaStream_t& stream,
paddle::Tensor* out);
@@ -103,5 +104,6 @@ CascadeAppendAttentionC8Kernel<paddle::bfloat16, paddle::bfloat16, true>(
const bool causal,
const bool is_decoder,
const bool enable_prefill,
const std::string& cache_quant_type_str,
cudaStream_t& stream,
paddle::Tensor* out);
custom_ops/gpu_ops/append_attn/template_instantiation/append_attention_c8_bfloat16_fp8_kernel.cu
+2
View File
@@ -54,6 +54,7 @@ template void CascadeAppendAttentionC8Kernel<paddle::bfloat16, paddle::float8_e4
const bool causal,
const bool is_decoder,
const bool enable_prefill,
const std::string& cache_quant_type_str,
cudaStream_t& stream,
paddle::Tensor* out);
@@ -98,5 +99,6 @@ template void CascadeAppendAttentionC8Kernel<paddle::bfloat16, paddle::float8_e4
const bool causal,
const bool is_decoder,
const bool enable_prefill,
const std::string& cache_quant_type_str,
cudaStream_t& stream,
paddle::Tensor* out);
custom_ops/gpu_ops/append_attn/template_instantiation/append_attention_c8_bfloat16_int8_kernel.cu
+2
View File
@@ -54,6 +54,7 @@ template void CascadeAppendAttentionC8Kernel<paddle::bfloat16, int8_t, false>(
const bool causal,
const bool is_decoder,
const bool enable_prefill,
const std::string& cache_quant_type_str,
cudaStream_t& stream,
paddle::Tensor* out);
@@ -100,5 +101,6 @@ template void CascadeAppendAttentionC8Kernel<paddle::bfloat16, int8_t, true>(
const bool causal,
const bool is_decoder,
const bool enable_prefill,
const std::string& cache_quant_type_str,
cudaStream_t& stream,
paddle::Tensor* out);
custom_ops/gpu_ops/append_attn/template_instantiation/append_attention_c8_float16_float16_kernel.cu
+2
View File
@@ -54,6 +54,7 @@ template void CascadeAppendAttentionC8Kernel<paddle::float16, paddle::float16, f
const bool causal,
const bool is_decoder,
const bool enable_prefill,
const std::string& cache_quant_type_str,
cudaStream_t& stream,
paddle::Tensor* out);
@@ -100,5 +101,6 @@ template void CascadeAppendAttentionC8Kernel<paddle::float16, paddle::float16, t
const bool causal,
const bool is_decoder,
const bool enable_prefill,
const std::string& cache_quant_type_str,
cudaStream_t& stream,
paddle::Tensor* out);
custom_ops/gpu_ops/append_attn/template_instantiation/append_attention_c8_float16_fp8_kerne.cu
+2
View File
@@ -54,6 +54,7 @@ template void CascadeAppendAttentionC8Kernel<paddle::float16, paddle::float8_e4m
const bool causal,
const bool is_decoder,
const bool enable_prefill,
const std::string& cache_quant_type_str,
cudaStream_t& stream,
paddle::Tensor* out);
@@ -99,5 +100,6 @@ template void CascadeAppendAttentionC8Kernel<paddle::float16, paddle::float8_e4m
const bool causal,
const bool is_decoder,
const bool enable_prefill,
const std::string& cache_quant_type_str,
cudaStream_t& stream,
paddle::Tensor* out);
custom_ops/gpu_ops/append_attn/template_instantiation/append_attention_c8_float16_int8_kerne.cu
+2
View File
@@ -54,6 +54,7 @@ template void CascadeAppendAttentionC8Kernel<paddle::float16, int8_t, false>(
const bool causal,
const bool is_decoder,
const bool enable_prefill,
const std::string& cache_quant_type_str,
cudaStream_t& stream,
paddle::Tensor* out);
@@ -99,5 +100,6 @@ template void CascadeAppendAttentionC8Kernel<paddle::float16, int8_t, true>(
const bool causal,
const bool is_decoder,
const bool enable_prefill,
const std::string& cache_quant_type_str,
cudaStream_t& stream,
paddle::Tensor* out);