chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

Multiple refactors of DeepSeek V32 and context parallel (#16305)

Browse Source
This commit is contained in:
Baizhou Zhang
2026-01-03 02:21:22 +08:00
committed by GitHub
parent 1cfd2b2ded
commit f07e76b229
7 changed files with 193 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
python/sglang/srt/server_args.py
View File

@@ -1065,15 +1065,26 @@ class ServerArgs:
logger.info("Use nsa attention backend for DeepSeek NSA.")
if not is_npu(): # CUDA GPU
self.enable_dp_attention = True
logger.warning("DP attention is enabled for DeepSeek NSA.")
if self.enable_nsa_prefill_context_parallel:
# TODO Supports moe_dense_tp_size != 1, kv cache dtype = "fp8",moe_a2a_backend non-deepep and cross-machine operation .
self.moe_dense_tp_size = 1
if self.nsa_prefill_cp_mode != "round-robin-split":
logger.warning(
f"Context parallel feature is still under experiment. It has only been verified on Hopper platform."
)
if self.nsa_prefill_cp_mode == "in-seq-split":
# TODO Supports moe_dense_tp_size != 1, kv cache dtype = "fp8",moe_a2a_backend non-deepep and cross-machine operation .
self.enable_dp_attention = True
self.moe_dense_tp_size = 1
self.moe_a2a_backend = "deepep"
self.ep_size = self.tp_size
self.kv_cache_dtype = "bf16"
logger.warning(
f"For in-seq split mode, we have the following restrictions: moe_dense_tp_size == 1, moe_a2a_backend == deepep, ep_size == tp_size, kv_cache_dtype == bf16, batch_size == 1"
)
else:
self.enable_dp_attention = True
self.moe_dense_tp_size = 1
assert (
self.dp_size == 1
), "For round-robin split mode, dp attention is not supported."
assert (
self.tp_size == 8
), "Current multi-machine CP support suffers from precision issues. So context parallel only support Single machine(tp_size == 8)"