Skip to content

perf(dsv41): the default prefill chunk is 4096 rows, not 512 #46

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
imD-5 wants to merge 1 commit into
base: deepseek-v41-tp2
Choose a base branch
from
+3 −1
Open

perf(dsv41): the default prefill chunk is 4096 rows, not 512 #46

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion src/tensorfold/families/deepseek_v41/cuda/engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,9 @@

from . import memtrace

PREFILL_CHUNK = int(os.environ.get("TF_DS_PREFILL_CHUNK") or 512)
# a prompt fills in chunks of this many rows: 4096 measured 28.14 s against 30.87 s for 2048 on a cold 64K prompt (two
# GB10), and 8192 overruns the allocator ceiling inside the MoE (exl3/experts.py:505)
PREFILL_CHUNK = int(os.environ.get("TF_DS_PREFILL_CHUNK") or 4096)
# the RDMA gather's slot in MiB (default 4.25; 8 before): fp32 gathers up to it go over RDMA writes, larger ones over
# NCCL. Decode's largest is a 16-row vocab-split head (4.14 MB); prefill chunks of 218-409 rows send 4.3-8 MB a gather
# (over NCCL at 4.25). Pinned host memory a rank: slot x TF_RDMA_SLOTS x (1 + world) (4.25 MiB x 4 x 3 = 51 MiB; 96 at 8)
Expand Down