Skip to content

Disable prefix cache for kimi vllm configs #926

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
Oseltamivir wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Disable prefix cache for kimi vllm configs #926

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d689db8
init
Oseltamivir Mar 23, 2026
097040e
fix cache dir
Oseltamivir Mar 23, 2026
3e2ebc0
Merge branch 'main' into disable-prefix
cquil11 Mar 24, 2026
04de3b2
Merge branch 'main' into disable-prefix
Oseltamivir Mar 25, 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
1 change: 1 addition & 0 deletions benchmarks/single_node/kimik2.5_fp4_b200.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@ vllm serve $MODEL --host 0.0.0.0 --port $PORT \
--reasoning-parser kimi_k2 \
--tool-call-parser kimi_k2 \
--compilation_config.pass_config.fuse_allreduce_rms true \
--no-enable-prefix-caching \
--trust-remote-code > $SERVER_LOG 2>&1 &

SERVER_PID=$!
Expand Down
1 change: 1 addition & 0 deletions benchmarks/single_node/kimik2.5_fp4_mi355x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,7 @@ vllm serve $MODEL --port $PORT \
--block-size=64 \
--disable-log-requests \
--trust-remote-code \
--no-enable-prefix-caching \
--mm-encoder-tp-mode data > $SERVER_LOG 2>&1 &

SERVER_PID=$!
Expand Down
1 change: 1 addition & 0 deletions benchmarks/single_node/kimik2.5_int4_h200.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@ vllm serve $MODEL --host 0.0.0.0 --port $PORT \
--tool-call-parser kimi_k2 \
--compilation_config.pass_config.fuse_allreduce_rms true \
--trust-remote-code \
--no-enable-prefix-caching \
--disable-log-requests > $SERVER_LOG 2>&1 &

SERVER_PID=$!
Expand Down
1 change: 1 addition & 0 deletions benchmarks/single_node/kimik2.5_int4_mi325x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@ vllm serve $MODEL --port $PORT \
--block-size=64 \
--disable-log-requests \
--trust-remote-code \
--no-enable-prefix-caching \
--mm-encoder-tp-mode data > $SERVER_LOG 2>&1 &

SERVER_PID=$!
Expand Down
1 change: 1 addition & 0 deletions benchmarks/single_node/kimik2.5_int4_mi355x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@ vllm serve $MODEL --port $PORT \
--block-size=64 \
--disable-log-requests \
--trust-remote-code \
--no-enable-prefix-caching \
--mm-encoder-tp-mode data > $SERVER_LOG 2>&1 &

SERVER_PID=$!
Expand Down
10 changes: 10 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1055,3 +1055,13 @@
- "Enable VLLM_USE_FLASHINFER_MOE_INT4=1 for Kimi K2.5 INT4 B200 benchmark"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/935

- config-keys:
- kimik2.5-int4-mi325x-vllm
- kimik2.5-int4-mi355x-vllm
- kimik2.5-int4-h200-vllm
- kimik2.5-fp4-mi355x-vllm
- kimik2.5-fp4-b200-vllm
description:
- "Disable prefix caching (--no-enable-prefix-caching) for all Kimi K2.5 benchmarks using random datasets"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/926

2 changes: 1 addition & 1 deletion runners/launch_h200-nb.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
#!/usr/bin/bash

export HF_HUB_CACHE_MOUNT="/home/gharunner/gharunners/hf-hub-cache/"
export HF_HUB_CACHE_MOUNT="/mnt/data/gharunners/hf-hub-cache/"
export PORT=8888

MODEL_CODE="${EXP_NAME%%_*}"
Expand Down
Loading