apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 08:16:42 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
Files
91536c827943608f56c93ae39c900de43ca151a0
FastDeploy/custom_ops/gpu_ops
History
chen f38b174a75
Some checks failed
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
Fix noaux_tc cuda Error 700 in CUDAGraph and Add wfp8apf8 moe quant method (#4115) 
* improve per_token_quant_fp8 performance

* support moe wfp8apf8

* check glm test

* fix noaux_tc op in cudagraph, support noaux_tc return the correct

* check

* check inf and overwrite score in noaux_tc

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-09-22 21:27:37 +08:00
..
append_attn
[CP]Glm45 air 2.2 (#4073)
2025-09-15 18:52:58 +08:00
common
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
custom_all_reduce
Add custom op declaration for all_reduce (#3473)
2025-08-20 20:29:58 +08:00
cutlass_extensions
[Optimize]support machete weight only gemm (#3561)
2025-08-28 09:49:58 +08:00
cutlass_kernels
optimize w4a8 decoding (#3050)
2025-07-28 22:20:13 +08:00
flash_mask_attn
[New Feature] fa3 支持flash mask (#3184)
2025-08-05 12:20:48 +08:00
fp8_gemm_with_cutlass
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
glog
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
int8_gemm_with_cutlass
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
machete
[CP2.2] Machete support group scale & wint8 & v1 loader (#4166)
2025-09-19 11:13:12 +08:00
mla_attn
[BugFix] Rename attention params of deepseekv3 (#2939)
2025-07-22 14:01:30 +08:00
moba_attn
[Feature] block sparse attention (#3668)
2025-08-29 19:46:30 +08:00
moe
【New Feature】集中式支持w4afp8 (#3644)
2025-08-28 10:53:24 +08:00
quantization
Fix noaux_tc cuda Error 700 in CUDAGraph and Add wfp8apf8 moe quant method (#4115)
2025-09-22 21:27:37 +08:00
sample_kernels
[OPs] Universal optimization and Fix early_stop cuda 700 (#3375)
2025-08-14 22:40:44 +08:00
speculate_decoding
[Feature][MTP]support new speculative decoding method named hybrid mtp with ngram (#3610)
2025-08-26 14:29:22 +08:00
w4afp8_gemm
【Fix bug] w4afp8 的nblock固定为256，并且fa3的append attn 增加mask参数 (#3771) (#3835)
2025-09-03 19:36:45 +08:00
wfp8afp8_sparse_gemm
【New Feature】支持Fp8 group Gemm 24稀疏 (#3463)
2025-08-19 02:54:47 -07:00
append_attention.cu
Add with_output version AppendAttention (#3302)
2025-08-28 17:10:18 +08:00
beam_search_softmax.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
cpp_extensions.cc
Fix noaux_tc cuda Error 700 in CUDAGraph and Add wfp8apf8 moe quant method (#4115)
2025-09-22 21:27:37 +08:00
cuda_multiprocess.h
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
dequant_int8.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
enforce_generation.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
env.h
[Sync] Update to latest code (#2679)
2025-07-03 15:43:53 +08:00
extract_text_token_output.cu
[Code Simplification] Refactor Post-processing in VL Model Forward Method (#2937)
2025-08-01 17:28:07 +08:00
fused_get_rope.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
fused_hadamard_quant_fp8.cu
[Optimize] Optimize tensorwise fp8 performance (#2729)
2025-07-07 20:06:28 +08:00
fused_rotary_position_encoding.cu
[Feature] DeepseekV3 use pd_build_static_op (#2948)
2025-07-22 15:03:41 +08:00
gather_idx.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
get_data_ptr_ipc.cu
Sync v2.0 version of code to github repo
2025-06-29 23:29:37 +00:00
get_img_boundaries.cc
[Feature] Multimodal Scheduler V1 (#3019)
2025-07-30 16:05:55 +08:00
get_mm_split_fuse.cc
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
get_output_ep.cc
[OPs] Universal optimization and Fix early_stop cuda 700 (#3375)
2025-08-14 22:40:44 +08:00
get_output_msg_with_topk.cc
[Feature] Online Chat API Support Return logprobs (#2777)
2025-07-10 16:33:40 +08:00
get_output.cc
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
get_padding_offset_system.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
get_padding_offset.cu
enable dcu ci (#3402)
2025-08-29 10:23:08 +08:00
get_position_ids_and_mask_encoder_batch.cu
[Feature] DeepseekV3 use pd_build_static_op (#2948)
2025-07-22 15:03:41 +08:00
helper.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
helper.h
Fix noaux_tc cuda Error 700 in CUDAGraph and Add wfp8apf8 moe quant method (#4115)
2025-09-22 21:27:37 +08:00
init_signal_layerwise.cc
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
ipc_sent_key_value_cache_by_remote_ptr.cu
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
merge_prefill_decode_output.cu
集中式支持fa3 (#3112)
2025-08-01 18:03:36 +08:00
msg_utils.h
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
multi_head_latent_attention.cu
[Feature] DeepseekV3 use pd_build_static_op (#2948)
2025-07-22 15:03:41 +08:00
ngram_mask.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
noaux_tc.cu
Fix noaux_tc cuda Error 700 in CUDAGraph and Add wfp8apf8 moe quant method (#4115)
2025-09-22 21:27:37 +08:00
noauxtc_kernel.h
Fix noaux_tc cuda Error 700 in CUDAGraph and Add wfp8apf8 moe quant method (#4115)
2025-09-22 21:27:37 +08:00
open_shm_and_get_meta_signal.cc
Sync v2.0 version of code to github repo
2025-06-29 23:29:37 +00:00
per_token_quant_fp8.cu
Support 45t fp8 8 GPU (#3659)
2025-08-28 10:52:53 +08:00
read_data_ipc.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
read_ids.py
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
read_temp_ids.py
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
rebuild_padding.cu
[Code Simplification] remove cum_offsets (#3410)
2025-08-18 20:21:25 +08:00
recover_decode_task.cu
[Feature] Support block scheduler v1 for FD (#2928)
2025-07-23 20:31:31 +08:00
remote_cache_kv_ipc.cc
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
remote_cache_kv_ipc.h
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
save_output_msg_with_topk.cc
[Feature] Online Chat API Support Return logprobs (#2777)
2025-07-10 16:33:40 +08:00
save_with_output_msg.cc
Supports DP+TP+EP hybrid parallel deployment strategy (#3489)
2025-08-26 00:04:01 -07:00
save_with_output_msg.h
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
save_with_output.cc
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
scaled_gemm_f8_i4_f16_gemm.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
scaled_gemm_f8_i4_f16_weight_quantize.cu
fix scaled_gemm_f8_i4_f16_weight_quantize input (#3685)
2025-08-29 11:04:04 +08:00
seqs2seqs.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
set_data_ipc.cu
dcu adapter ernie45t (#2756)
2025-07-09 18:56:27 +08:00
set_flags.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
set_mask_value.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
set_value_by_flags.cu
Adapt for iluvatar gpu (#2684)
2025-07-07 16:53:14 +08:00
share_external_data.cu
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
step_reschedule.cu
Sync v2.0 version of code to github repo
2025-06-29 23:29:37 +00:00
step_system_cache.cu
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
step.cu
Adapt for iluvatar gpu (#2684)
2025-07-07 16:53:14 +08:00
stop_generation_multi_ends.cu
[stop sequence] support stop sequence (#3025)
2025-07-29 14:17:37 +08:00
stop_generation.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
swap_cache_batch.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
swap_cache.cu
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
system2group.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
text_image_gather_scatter.cu
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
text_image_index_out.cu
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
token_penalty_multi_scores.cu
[Feature] support bad_words (#3055)
2025-07-30 09:31:29 +08:00
token_penalty_only_once.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
token_transfer.hpp
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
transfer_output.cc
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
tune_cublaslt_gemm.cu
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
unset_data_ipc.cu
[feat] support prefix cache clearing when /clear_load_weight is called (#4091)
2025-09-16 11:11:20 +08:00
update_inputs_beam.cu
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
update_inputs_v1.cu
[Feature] Support block scheduler v1 for FD (#2928)
2025-07-23 20:31:31 +08:00
update_inputs.cu
Adapt for iluvatar gpu (#2684)
2025-07-07 16:53:14 +08:00
update_split_fuse_input.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00