Skip to content

[DNM][AMD] agentx-v0.4 #1654

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
seungrokj wants to merge 14 commits into
base: chore/agentx-v0.4
Choose a base branch
from
+868 −727
Open

[DNM][AMD] agentx-v0.4 #1654

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
7a86001
[AMD] agentx-v0.4: add MiniMax/Kimi lmcache agentic entries, refactor…
seungrokj Jun 3, 2026
19d1ca5
[AMD] minimaxm2.5 agentic: change LMCACHE_CHUNK_SIZE default from 256…
seungrokj Jun 3, 2026
d184078
[AMD] agentx-v0.4: add MODEL_PATH support and --served-model-name for…
seungrokj Jun 3, 2026
d2b2826
[AMD] kimik2.5-fp4-mi355x-vllm-agentic-lmcache: fix config, use v0.21…
seungrokj Jun 3, 2026
dc999ef
[AMD] agentx-v0.4: fix configs for MiniMax/Kimi/Qwen agentic entries
seungrokj Jun 3, 2026
fc0d0d4
[AMD] qwen3.5-fp8-mi355x-sglang-agentic-hicache: fix runner to mi355x
seungrokj Jun 3, 2026
fe3afa9
[AMD] qwen3.5-fp8-mi355x-sglang-agentic-hicache: update conc-list to …
seungrokj Jun 3, 2026
dc25a0b
[AMD] minimaxm2.5-fp8-mi355x-vllm-agentic: add lmcache variant config…
seungrokj Jun 3, 2026
34cd6b0
[AMD] glm5.1-fp4-mi355x-sglang-agentic: add hicache variant config an…
seungrokj Jun 3, 2026
3707963
[AMD] qwen3.5-fp8-mi355x-sglang-agentic: update conc-list and remove …
seungrokj Jun 4, 2026
b3b3476
[AMD] qwen3.5-fp4-mi355x-sglang-agentic: add hicache variant config a…
seungrokj Jun 4, 2026
56d9dc5
[AMD] amd-master: fix entry names and tp for qwen3.5-fp4 and minimaxm…
seungrokj Jun 4, 2026
c697c16
[AMD] minimaxm2.5-fp4-mi355x-agentic: increase lmcache DRAM size
seungrokj Jun 4, 2026
6dbef81
[AMD] minimaxm2.5-fp8-mi355x-agentic: increase lmcache DRAM size
seungrokj Jun 4, 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
35 changes: 28 additions & 7 deletions .github/configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -872,6 +872,21 @@ minimaxm2.5-fp4-mi355x-atom:
- { tp: 4, conc-start: 4, conc-end: 128 }
- { tp: 8, conc-start: 4, conc-end: 16 }

minimaxm2.5-fp4-mi355x-vllm-agentic-lmcache:
image: vllm/vllm-openai-rocm:v0.22.0
model: amd/MiniMax-M2.5-MXFP4
model-prefix: minimaxm2.5
runner: mi355x
precision: fp4
framework: vllm
multinode: false
scenarios:
agentic-coding:
- duration: 1800
search-space:
- { tp: 1, ep: 1, offloading: none, conc-list: [4, 8, 16, 32, 40, 48] }
- { tp: 1, ep: 1, offloading: lmcache, conc-list: [4, 8, 16, 32, 40, 48] }

minimaxm2.5-fp4-mi355x-vllm:
image: vllm/vllm-openai-rocm:v0.22.0
model: amd/MiniMax-M2.5-MXFP4
Expand Down Expand Up @@ -2518,6 +2533,16 @@ kimik2.5-fp4-mi355x-vllm-agentic:
- { tp: 4, offloading: none, conc-list: [16, 24, 32, 40] }
- { tp: 4, offloading: cpu, conc-list: [16, 24, 32, 40] }

kimik2.5-fp4-mi355x-vllm-agentic-lmcache:
image: vllm/vllm-openai-rocm:v0.22.0
model: amd/Kimi-K2.5-MXFP4
model-prefix: kimik2.5
agentic-coding:
- duration: 1800
search-space:
- { tp: 4, ep: 1, offloading: none, conc-list: [4, 8, 16, 32, 40, 48, 56, 64, 72] }
- { tp: 4, ep: 1, offloading: lmcache, conc-list: [4, 8, 16, 32, 40, 48, 56, 64, 72] }
Comment thread
cursor[bot] marked this conversation as resolved.
Outdated
Comment thread
seungrokj marked this conversation as resolved.
Outdated

minimaxm2.5-fp8-mi355x-vllm-agentic:
image: vllm/vllm-openai-rocm:v0.22.0
model: MiniMaxAI/MiniMax-M2.5
Expand Down Expand Up @@ -2574,19 +2599,15 @@ minimaxm2.5-fp8-mi325x-vllm-agentic:
- { tp: 4, offloading: cpu, conc-list: [16, 20, 24, 28, 32] }

qwen3.5-fp8-mi355x-sglang-agentic-hicache:
image: lmsysorg/sglang-rocm:v0.5.12-rocm720-mi35x-20260521
image: lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260531
model: Qwen/Qwen3.5-397B-A17B-FP8
model-prefix: qwen3.5
runner: mi355x
precision: fp8
framework: sglang
multinode: false
scenarios:
agentic-coding:
- duration: 1800
search-space:
- { tp: 8, ep: 1, offloading: none, conc-list: [1, 2, 4, 8, 16, 32] }
- { tp: 8, ep: 1, offloading: hicache, conc-list: [16, 32, 48, 64] }
- { tp: 4, ep: 1, offloading: none, conc-list: [4, 8, 16, 32, 40, 48, 56, 64, 128] }
- { tp: 4, ep: 1, offloading: hicache, conc-list: [4, 8, 16, 32, 40, 48, 56, 64, 128] }
Comment thread
cursor[bot] marked this conversation as resolved.
Outdated

dsv4-fp4-mi355x-vllm-agentic:
image: vllm/vllm-openai-rocm:v0.22.0
Expand Down
Loading