BBuf/vllm-minimax-optimization
skills/model-optimization/vllm/vllm-minimax-optimization/SKILL.md
PR-backed optimization manual for MiniMax M1 / M2 / VL in vLLM. Use when an engineer needs to audit, debug, extend, or document MiniMaxText01, MiniMax-M1, MiniMax-M2, MiniMax-VL-01, LoRA, and Eagle3 support in vLLM.
$ install --global
skillsauthnpx skillsauth add BBuf/AI-Infra-Auto-Driven-SKILLS vllm-minimax-optimizationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 2, 2026, 7:11 AM296.0s1 file scanned
SKILL.md
- name:
- vllm-minimax-optimization
- description:
- PR-backed optimization manual for MiniMax M1 / M2 / VL in vLLM. Use when an engineer needs to audit, debug, extend, or document MiniMaxText01, MiniMax-M1, MiniMax-M2, MiniMax-VL-01, LoRA, and Eagle3 support in vLLM.
vLLM MiniMax M1 / M2 / VL Optimization
Overview
This skill covers MiniMaxText01, MiniMax-M1, MiniMax-M2, MiniMax-VL-01, LoRA, and Eagle3 support in vLLM.
Evidence snapshot:
- vLLM mainline checked around
0f7be0f2f76814f80f9091220a5fbbb53912ad00 - Support status: supported on current mainline
- Canonical PR notes:
references/pr-history.md - History mirrors:
model-pr-optimization-history/vllm/minimax/README.zh.mdandREADME.en.md
Non-Negotiable Evidence Rule
Use skills/model-optimization/model-pr-diff-dossier/SKILL.md as the production bar.
Every PR cited for this family must be based on diff reading, not only PR titles.
Runtime Surfaces
vllm/vllm/model_executor/models/minimax_text_01.pyvllm/vllm/model_executor/models/minimax_m2.pyvllm/vllm/model_executor/models/minimax_vl_01.py
Current Main Summary
- MiniMax support evolved from the text-01 path into M1/M2 and VL variants.
- Today the key production surfaces are linear-attention correctness, VL processor behavior, LoRA, and Eagle3 on M2.
Key Landed PRs
- #13454
Support MiniMaxText01 model inference: Landed the original MiniMax text runtime. - #16328
support MiniMax-VL-01 model: Added the multimodal MiniMax-VL path. - #19677
Add support for MiniMaxM1ForCausalLM: Connected the M1 checkpoint alias to the shared MiniMax runtime. - #27535
Support MiniMax-M2 Model: Brought the M2 generation into mainline. - #32763
Complete LoRA support for MiniMaxM2: Finished missing adapter wiring in the M2 family. - #37512
MiniMax-M2: add Eagle3 speculative decoding support: Enabled the draft-model acceleration path for MiniMax M2.
Open Optimization Items
- Re-run PR search before claiming new support beyond the checked mainline commit.
Validation Lanes
- MiniMax text and VL startup.
- M2 LoRA adapter application.
- Eagle3 speculative decode on M2.
- Reasoning and tool parser streaming for MiniMax checkpoints.
Related Skills
BBuf/sglang-humanize-review
development
VerifiedTrustedCommunity
Perform SGLang code review in the style of human maintainers by consulting the full non-agent PR review episode corpus from project start through the latest refresh (June 2026), including inline review threads, top-level PR comments, review submissions, original multilingual text, and multi-round discussions. Use when reviewing SGLang PRs, diffs, patches, or local changes for correctness, tests, performance, GPU/runtime risks, API compatibility, and maintainability.
531SKILL.mdUpdated May 21, 2026
BBuf/model-pr-history-knowledge
documentation
VerifiedTrustedCommunity
Use when an SGLang, vLLM, or TensorRT-LLM serving/model optimization task needs prior model-family PR evidence. Query and read the PR-driven history docs under model-pr-optimization-history before choosing source paths, fast paths, kernel/fusion ideas, regression risks, or validation lanes.
531SKILL.mdUpdated May 17, 2026
BBuf/vllm-sota-humanize-loop
development
VerifiedTrustedCommunity
Run an autonomous Humanize-governed vLLM SOTA performance loop for one LLM model: first perform the fixed fair vLLM/SGLang/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches vLLM code, optionally uses ncu-report-skill for kernel evidence, and revalidates until vLLM matches or beats the best observed framework under the same workload and SLA.
423SKILL.mdUpdated May 27, 2026
BBuf/llm-pipeline-analysis
devops
VerifiedTrustedCommunity
Inspect LLM torch profiler traces at forward-pass, layer, and kernel level. Use when you need layer timings, anchor-kernel boundaries, representative kernel flows, or Perfetto time ranges.
423SKILL.mdUpdated May 21, 2026