Skip to content

[NV] Add Kimi K2.5 FP4 B200/B300 EP sweep #1658

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

Draft
jasonlizhengjian wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

[NV] Add Kimi K2.5 FP4 B200/B300 EP sweep #1658

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
380b685
Add Kimi K2.5 EP sweep points
jasonlizhengjian Jun 3, 2026
8c2f793
Add Kimi K2.5 EP sweep changelog
jasonlizhengjian Jun 3, 2026
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
8 changes: 8 additions & 0 deletions .github/configs/nvidia-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2661,12 +2661,16 @@ kimik2.5-fp4-b200-vllm:
osl: 1024
search-space:
- { tp: 8, ep: 1, conc-start: 4, conc-end: 4 }
- { tp: 8, ep: 8, conc-start: 4, conc-end: 4 }
- { tp: 4, ep: 1, conc-start: 4, conc-end: 64 }
- { tp: 4, ep: 4, conc-start: 4, conc-end: 64 }
- isl: 8192
osl: 1024
search-space:
- { tp: 8, ep: 1, conc-start: 4, conc-end: 4 }
- { tp: 8, ep: 8, conc-start: 4, conc-end: 4 }
- { tp: 4, ep: 1, conc-start: 4, conc-end: 64 }
- { tp: 4, ep: 4, conc-start: 4, conc-end: 64 }

# NOTE: At the time of submission, https://docs.vllm.ai/projects/recipes/en/latest/moonshotai/Kimi-K2.5.html
# does not have a B300-specific recipe, so this config reuses the existing
Expand Down Expand Up @@ -2714,12 +2718,16 @@ kimik2.5-fp4-b300-vllm:
osl: 1024
search-space:
- { tp: 8, ep: 1, conc-start: 4, conc-end: 4 }
- { tp: 8, ep: 8, conc-start: 4, conc-end: 4 }
- { tp: 4, ep: 1, conc-start: 4, conc-end: 64 }
- { tp: 4, ep: 4, conc-start: 4, conc-end: 64 }
- isl: 8192
osl: 1024
search-space:
- { tp: 8, ep: 1, conc-start: 4, conc-end: 4 }
- { tp: 8, ep: 8, conc-start: 4, conc-end: 4 }
- { tp: 4, ep: 1, conc-start: 4, conc-end: 64 }
- { tp: 4, ep: 4, conc-start: 4, conc-end: 64 }

dsr1-fp8-b200-sglang-mtp:
image: lmsysorg/sglang:v0.5.12-cu130
Expand Down
9 changes: 8 additions & 1 deletion benchmarks/single_node/fixed_seq_len/kimik2.5_fp4_b200.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@ source "$(dirname "$0")/../../benchmark_lib.sh"
check_env_vars \
MODEL \
TP \
EP_SIZE \
CONC \
ISL \
OSL \
Expand Down Expand Up @@ -39,9 +40,15 @@ start_gpu_monitor
# benchmarks/single_node/agentic/kimik2.5_fp4_b200.sh).
export VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=0

EP_ARGS=()
if [ "$EP_SIZE" -gt 1 ]; then
EP_ARGS=(--enable-expert-parallel)
fi

set -x
vllm serve $MODEL --host 0.0.0.0 --port $PORT \
--tensor-parallel-size=$TP \
"${EP_ARGS[@]}" \
--gpu-memory-utilization 0.90 \
--max-model-len $MAX_MODEL_LEN \
--max-num-seqs $CONC \
Expand Down Expand Up @@ -82,4 +89,4 @@ fi

# Stop GPU monitoring
stop_gpu_monitor
set +x
set +x
7 changes: 7 additions & 0 deletions benchmarks/single_node/fixed_seq_len/kimik2.5_fp4_b300.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ source "$(dirname "$0")/../../benchmark_lib.sh"
check_env_vars \
MODEL \
TP \
EP_SIZE \
CONC \
ISL \
OSL \
Expand Down Expand Up @@ -47,9 +48,15 @@ fi
# Start GPU monitoring (power, temperature, clocks every second)
start_gpu_monitor

EP_ARGS=()
if [ "$EP_SIZE" -gt 1 ]; then
EP_ARGS=(--enable-expert-parallel)
fi

set -x
vllm serve $MODEL_PATH --served-model-name $MODEL --host 0.0.0.0 --port $PORT \
--tensor-parallel-size $TP \
"${EP_ARGS[@]}" \
--gpu-memory-utilization 0.90 \
--max-model-len $MAX_MODEL_LEN \
--max-num-seqs $CONC \
Expand Down
7 changes: 7 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3430,3 +3430,10 @@
- "Image: vllm/vllm-openai:v0.20.1"
- "Same 1k/1k and 8k/1k search space as gb300, plus a new tp8-1p1d at low concurrencies for both ISLs"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1652

- config-keys:
- kimik2.5-fp4-b200-vllm
- kimik2.5-fp4-b300-vllm
description:
- "Add expert-parallel sweep points for Kimi K2.5 FP4 B200/B300 vLLM aggregate benchmarks"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1658