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

Sync v2.0 version of code to github repo

Browse Source
This commit is contained in:
Jiang-Jia-Jun
2025-06-29 23:29:37 +00:00
parent d151496038
commit 92c2cfa2e7
597 changed files with 78776 additions and 22905 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
benchmarks/yaml/eb45-32k-wint4-tp4_decode.yaml Normal file
View File

@@ -0,0 +1,15 @@
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