apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[CE]add pd router and wint4 tp4 config (#5554)

Browse Source
This commit is contained in:
xiegegege
2025-12-15 15:25:14 +08:00
committed by GitHub
parent 7b0fdf7055
commit 97e340eb14
3 changed files with 36 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
benchmarks/yaml/eb45-32k-wint4-ep4-tp4.yaml Normal file
View File

@@ -0,0 +1,7 @@
num_gpu_blocks_override: 1024
max_model_len: 8192
max_num_seqs: 64
data_parallel_size: 4
tensor_parallel_size: 1
enable_expert_parallel: True
quantization: wint4

16
benchmarks/yaml/eb45-32k-wint4-tp4_decode_router.yaml Normal file
View File

@@ -0,0 +1,16 @@
max_model_len: 32768
max_num_seqs: 256
gpu_memory_utilization: 0.9
kv_cache_ratio: 0.8
tensor_parallel_size: 4
cache_queue_port: 55663
enable_chunked_prefill: True
splitwise_role: decode
engine_worker_queue_port: 6678
cache_transfer_protocol: "rdma,ipc"
rdma_comm_ports: "7671,7672,7673,7674"
pd_comm_port: "2334"
max_num_batched_tokens: 384
max_num_partial_prefills: 3
max_long_partial_prefills: 3
quantization: wint4

13
benchmarks/yaml/eb45-32k-wint4-tp4_prefill_router.yaml Normal file
View File

@@ -0,0 +1,13 @@
max_model_len: 32768
max_num_seqs: 16
gpu_memory_utilization: 0.9
kv_cache_ratio: 0.9
tensor_parallel_size: 4
splitwise_role: prefill
enable_prefix_caching: True
cache_queue_port: 55664
engine_worker_queue_port: 6677
cache_transfer_protocol: "rdma,ipc"
rdma_comm_ports: "7675,7676,7677,7678"
pd_comm_port: "2333"
quantization: wint4