Skip to content

perf(agentx): sweep Kimi K3 with LMCache dev114 / 使用 LMCache dev114 扫描 Kimi K3 #2889

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

Merged
Oseltamivir merged 8 commits into from
Sep 10, 2026
+12 −3
Merged

perf(agentx): sweep Kimi K3 with LMCache dev114 / 使用 LMCache dev114 扫描 Kimi K3 #2889

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
5d52cb0
perf(agentx): sweep Kimi K3 with LMCache dev104
hyukjlee Sep 8, 2026
47ff4e6
docs(perf): link Kimi K3 LMCache sweep PR
hyukjlee Sep 8, 2026
a727411
docs: remove unrelated placeholder edits
hyukjlee Sep 8, 2026
3a8e298
fix(agentx): advance Kimi K3 LMCache nightly
hyukjlee Sep 9, 2026
86996d1
Merge origin/main into amd/k3-mi355x-lmcache-dev106-full-sweep
hyukjlee Sep 9, 2026
35a9640
fix(agentx): advance Kimi K3 LMCache to dev114
hyukjlee Sep 9, 2026
a52fa38
Merge remote-tracking branch 'origin/main' into amd/k3-mi355x-lmcache…
hyukjlee Sep 9, 2026
b2f1f4f
Merge branch 'main' into amd/k3-mi355x-lmcache-dev104-full-sweep
seungrokj Sep 10, 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
2 changes: 1 addition & 1 deletion benchmarks/single_node/agentic/kimik3_fp4_mi355x_mtp.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -149,7 +149,7 @@ case "${KV_OFFLOAD_BACKEND:-}" in
lmcache)
require_agentic_kv_offload_backend "$KV_OFFLOAD_BACKEND"

LMCACHE_VERSION=0.5.5.dev89+rocm7.2
LMCACHE_VERSION=0.5.5.dev114+rocm7.2
LMCACHE_ROCM_INDEX="https://github.com/LMCache/LMCache/releases/expanded_assets/nightly-rocm"

agentic_pip_install --quiet --no-cache-dir --no-deps \
Expand Down
4 changes: 2 additions & 2 deletions configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -637,8 +637,8 @@ kimik3-fp4-mi355x-vllm-agentic-mtp:
- dram-utilization: 0.60
search-space:
- { tp: 8, ep: 1, dcp-size: 1, kv-offloading: none, conc-list: [1] , spec-decoding: mtp}
- { tp: 8, ep: 1, dcp-size: 1, kv-offloading: dram, kv-offload-backend: { name: lmcache, version: "0.5.5.dev89+rocm7.2" }, conc-list: [4, 8, 10, 12, 14], spec-decoding: mtp }
- { tp: 8, ep: 1, dcp-size: 8, kv-offloading: dram, kv-offload-backend: { name: lmcache, version: "0.5.5.dev89+rocm7.2" }, conc-list: [44, 48, 52], spec-decoding: mtp }
- { tp: 8, ep: 1, dcp-size: 1, kv-offloading: dram, kv-offload-backend: { name: lmcache, version: "0.5.5.dev114+rocm7.2" }, conc-list: [4, 8, 10, 12, 14], spec-decoding: mtp }
- { tp: 8, ep: 1, dcp-size: 8, kv-offloading: dram, kv-offload-backend: { name: lmcache, version: "0.5.5.dev114+rocm7.2" }, conc-list: [44, 48], spec-decoding: mtp }

# Kimi-K3 MXFP4 agentic-coding benchmark on MI355X via ATOM with DSpark
# speculative decoding. Acceptance is pinned to the committed golden curve in
Expand Down
9 changes: 9 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6970,6 +6970,15 @@
- "Resolve draft-model jobs through the existing B200 SGLang speculative recipe and the staged DeepSeek-V4-Pro-0813 checkpoint."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2821

- config-keys:
- kimik3-fp4-mi355x-vllm-agentic-mtp
scenario-type:
- agentic-coding
description:
- "Upgrade the Kimi-K3 MI355X vLLM AgentX LMCache build from 0.5.5.dev89+rocm7.2 to 0.5.5.dev114+rocm7.2 from the nightly ROCm release index; the rolling release no longer publishes the intermediate 0.5.5.dev104+rocm7.2 wheel."
- "Preserve the image, runtime settings, and topology from the full sweep in Actions run 33773561410; run concurrency 1 without offload and LMCache concurrencies 4, 8, 10, 12, 14, 44, and 48, with 48 as the upper bound."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2889

@cursor cursor Bot Sep 9, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Changelog entry not appended at end

Medium Severity

The new perf-changelog.yaml entry is inserted ahead of the existing #2851 block instead of after every historical entry. Merge-time validation requires a byte-for-byte historical prefix and treats prior entries as position-immutable, so this placement breaks the append-only changelog contract and will fail reuse-merge preparation.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit a52fa38. Configure here.


- config-keys:
- dsv4-fp4-mi355x-vllm
- dsv4-fp4-mi355x-vllm-mtp
Expand Down