Skip to content

[Klaud Cold] Update minimaxm3-fp4-b300-vllm-agentic-mtp vLLM image to nightly-8a728663c1c3eeace834a95f5654fa653cc1998c and move to cluster:b300-dsxe #2883

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
functionstackx wants to merge 2 commits into
base: main
Choose a base branch
from
+12 −2
Open

[Klaud Cold] Update minimaxm3-fp4-b300-vllm-agentic-mtp vLLM image to nightly-8a728663c1c3eeace834a95f5654fa653cc1998c and move to cluster:b300-dsxe #2883

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
35705df
[Klaud Cold] Update minimaxm3-fp4-b300-vllm-agentic-mtp vLLM image to…
functionstackx Sep 8, 2026
3f0bc9a
Re-pin to the 2026-09-04 vLLM nightly: the 09-05 FlashAttention sync …
functionstackx Sep 8, 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
4 changes: 2 additions & 2 deletions configs/nvidia-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7624,10 +7624,10 @@ qwen3.5-fp4-gb200-dynamo-sglang-agentic-mtp:
- "CONFIG_FILE=recipes/sglang/qwen3.5/gb200-fp4/agentic/agg-gb200-tp2ep2-mtp-hicache.yaml"

minimaxm3-fp4-b300-vllm-agentic-mtp:
image: vllm/vllm-openai:nightly-1dc464d42681d22f38caf1fdc1eb632dc4421c45
image: vllm/vllm-openai:nightly-8a728663c1c3eeace834a95f5654fa653cc1998c
model: nvidia/MiniMax-M3-NVFP4
model-prefix: minimaxm3
runner: cluster:b300-nv
runner: cluster:b300-dsxe
precision: fp4
framework: vllm
multinode: false
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 @@ -6958,3 +6958,13 @@
- "Expand the TP8 and TP4/EP1 sweep coverage through concurrency 640."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2866


- config-keys:
- minimaxm3-fp4-b300-vllm-agentic-mtp
scenario-type:
- agentic-coding
description:
- "Update vLLM image from vllm/vllm-openai:nightly-1dc464d42681d22f38caf1fdc1eb632dc4421c45 (2026-08-30 nightly) to vllm/vllm-openai:nightly-d9105ea8001e0a6d77a96327d17515bb5791fb36 (2026-09-07 nightly, digest sha256:254eebf919e8b7b0d530d97fccc606c36f380ff6724d64bc190951bec1aee838, tag commit vllm-project/vllm@d9105ea8; Docker Hub last pushed 2026-09-07T06:16:01Z), the same tag the B200/H100/H200 MiniMax-M3 AgentX recipes moved to in #2860/#2874/#2875. benchmarks/single_node/agentic/minimaxm3_fp4_b300_mtp.sh is unchanged: EAGLE3 with the Inferact MiniMax-M3 EAGLE3-GQA draft on FLASH_ATTN, golden synthetic acceptance length 2.78, fp8 KV, max-cudagraph-capture-size 512; the TP8/TP4/TP2 grids with vllm-simple DRAM offload are unchanged."
- "Move the recipe from the retired cluster:b300-nv fleet (launcher and runner labels removed in #2826) to cluster:b300-dsxe so the sweep has a runner to schedule on. The runner change means this is not an append-only bump: the whole curve reruns on DSXE."
- "Re-pin from vllm/vllm-openai:nightly-d9105ea8001e0a6d77a96327d17515bb5791fb36 (2026-09-07 nightly) to vllm/vllm-openai:nightly-8a728663c1c3eeace834a95f5654fa653cc1998c (2026-09-04 nightly, digest sha256:f5df5cc3302b5f404848c4eca88d7bf7ed5226e151c056da22816d7734644d67; Docker Hub last pushed 2026-09-04T06:18:14Z, tag commit vllm-project/vllm@8a728663). Nightlies from 2026-09-05 onward carry vllm-project/vllm@4ee259551 (Sync FA with upstream, #54819), which moves vllm-flash-attn to 506341a1; on Blackwell the EAGLE3 draft runs FLASH_ATTN through the FA4 CuTe path and, with the fp8 KV cache, its descale tensors now fail to_cute_tensor with RuntimeError: Expected strides[leading_dim] == 1, but got 0 during CUDA-graph memory profiling, so the engine never starts (B200 run 34168437161). The 2026-09-04 nightly is the newest build still on vllm-flash-attn 06bdd47c, the same FA pin as the recipe's previous 2026-08-30 image, and the same vllm commit the MI355X MiniMax-M3 vLLM AgentX recipe already runs (nightly-8a728663). No vllm fix has landed on main as of 2026-09-08T03:00Z."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2883
Loading