Repository navigation
[AgentX] MiniMax-M3.1-Flash B300 SGLang: add TP2 and TP4 points / [AgentX] MiniMax-M3.1-Flash B300 SGLang：新增 TP2 和 TP4 点 #4726
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.
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
Merged
Changes from all commits
Commits
Show all changes
12 commits
Select commit
Hold shift + click to select a range
cc407c3
add b300 sglang points
ispobock 0cffd4c
fill pr link
ispobock f69cefc
add tp2 larger kv pool points
ispobock e90debd
lower mem fraction for larger kv pool points
ispobock 0979dfd
Merge remote-tracking branch 'origin/main' into minimaxm31flash-b300-…
ispobock 6bd10ab
keep tp2 c50 larger kv pool point
ispobock b3e11b9
Merge remote-tracking branch 'origin/main' into minimaxm31flash-b300-…
ispobock ab42462
add back tp2 c52 larger kv pool point
ispobock 1a4fd4d
add tp4 c17 point
ispobock 54d0a46
Merge remote-tracking branch 'origin/main' into minimaxm31flash-b300-…
ispobock b3a2817
Merge remote-tracking branch 'origin/main' into minimaxm31flash-b300-…
ispobock 04a5e36
drop tp4 c17 point
ispobock File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
117 changes: 117 additions & 0 deletions
117
...gle_node/srt-slurm-recipes/minimaxm31flash/sglang/b300-fp4-mtp/agentic-tp2-spf-extra.yaml
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,117 @@ | ||
| base: | ||
| schema: 2 | ||
| name: minimaxm31flash-fp4-b300-sglang-agentic-tp2-spf-extra | ||
| resources: | ||
| gpu_type: b300 | ||
| gpus_per_node: 8 | ||
| frontend: | ||
| type: sglang | ||
| enable_multiple_frontends: false | ||
| observability: | ||
| enabled: false | ||
| tachometer: | ||
| enabled: false | ||
| engine: sglang | ||
| # Cold loads of the 250 GB checkpoint plus JIT MSA kernel builds and graph capture outlast the default. | ||
| health_check: | ||
| max_attempts: 1440 | ||
| interval_seconds: 5 | ||
| roles: | ||
| agg: | ||
| nodes: 1 | ||
| workers: 1 | ||
| gpus: 2 | ||
| # Serve flags follow the cookbook's B300 cells at | ||
| # https://docs.sglang.io/cookbook/autoregressive/MiniMax/MiniMax-M3.1. | ||
| args: | ||
| served-model-name: MiniMaxAI/MiniMax-M3.1-Flash | ||
| trust-remote-code: true | ||
| reasoning-parser: minimax-m3 | ||
| tool-call-parser: minimax-m3 | ||
| # Seven-token DSpark, the bundled draft's dspark_block_size. Throughput runs | ||
| # switch to synthetic acceptance at the golden acceptance length. | ||
| speculative-algorithm: DSPARK | ||
| speculative-dspark-block-size: 7 | ||
| speculative-use-block-verification: true | ||
| # FP8 draft KV, as vLLM's DSpark drafter uses; bf16 costs ~10 GB of HBM per rank. | ||
| speculative-draft-kv-cache-dtype: fp8_e4m3 | ||
| cuda-graph-backend-prefill: breakable | ||
| tokenizer-worker-num: 8 | ||
| watchdog-timeout: 3600 | ||
| enable-metrics: true | ||
| env: | ||
| PYTHONNOUSERSITE: '1' | ||
| PYTHONUNBUFFERED: '1' | ||
| SGLANG_TIMEOUT_KEEP_ALIVE: '1800' | ||
| FMHA_SM100_ALLOW_JIT: '1' | ||
| benchmark: | ||
| env: | ||
| # Warmup can leave bytes unacknowledged past AIPerf's 30 s default. | ||
| AIPERF_HTTP_TCP_USER_TIMEOUT: '900000' | ||
| AIPERF_REQUIRED_SERVER_METRIC_PREFIX: 'sglang:' | ||
|
|
||
| # 2x CONC (AgentX subagent fan-out); the decode graph batch matches it. | ||
| override_tp2_c44_spf_interval32: | ||
| roles: | ||
| agg: | ||
| args: | ||
| tensor-parallel-size: 2 | ||
| moe-runner-backend: flashinfer_trtllm_routed | ||
| chunked-prefill-size: 8192 | ||
| max-running-requests: 88 | ||
| cuda-graph-max-bs-decode: 88 | ||
| mem-fraction-static: 0.92 | ||
| enable-hierarchical-cache: true | ||
| hicache-size: 370 | ||
| hicache-write-policy: write_back | ||
| schedule-policy: shortest-prefill-first | ||
| prefill-decode-interval: 32 | ||
| stream-interval: 20 | ||
| benchmark: | ||
| env: | ||
| CONC: '44' | ||
| KV_OFFLOADING: dram | ||
|
|
||
| # A larger HBM KV pool keeps more of the reused prefixes on device, so fewer are | ||
| # reloaded from host DRAM. | ||
| override_tp2_c50_spf_interval20_mem093: | ||
| roles: | ||
| agg: | ||
| args: | ||
| tensor-parallel-size: 2 | ||
| moe-runner-backend: flashinfer_trtllm_routed | ||
| chunked-prefill-size: 8192 | ||
| max-running-requests: 100 | ||
| cuda-graph-max-bs-decode: 100 | ||
| mem-fraction-static: 0.93 | ||
| enable-hierarchical-cache: true | ||
| hicache-size: 370 | ||
| hicache-write-policy: write_back | ||
| schedule-policy: shortest-prefill-first | ||
| prefill-decode-interval: 20 | ||
| stream-interval: 20 | ||
| benchmark: | ||
| env: | ||
| CONC: '50' | ||
| KV_OFFLOADING: dram | ||
|
|
||
| override_tp2_c52_spf_interval20_mem093: | ||
| roles: | ||
| agg: | ||
| args: | ||
| tensor-parallel-size: 2 | ||
| moe-runner-backend: flashinfer_trtllm_routed | ||
| chunked-prefill-size: 8192 | ||
| max-running-requests: 104 | ||
| cuda-graph-max-bs-decode: 104 | ||
| mem-fraction-static: 0.93 | ||
| enable-hierarchical-cache: true | ||
| hicache-size: 370 | ||
| hicache-write-policy: write_back | ||
| schedule-policy: shortest-prefill-first | ||
| prefill-decode-interval: 20 | ||
| stream-interval: 20 | ||
| benchmark: | ||
| env: | ||
| CONC: '52' | ||
| KV_OFFLOADING: dram |
95 changes: 95 additions & 0 deletions
95
...gle_node/srt-slurm-recipes/minimaxm31flash/sglang/b300-fp4-mtp/agentic-tp4-spf-extra.yaml
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,95 @@ | ||
| base: | ||
| schema: 2 | ||
| name: minimaxm31flash-fp4-b300-sglang-agentic-tp4-spf-extra | ||
| resources: | ||
| gpu_type: b300 | ||
| gpus_per_node: 8 | ||
| frontend: | ||
| type: sglang | ||
| enable_multiple_frontends: false | ||
| observability: | ||
| enabled: false | ||
| tachometer: | ||
| enabled: false | ||
| engine: sglang | ||
| # Cold loads of the 250 GB checkpoint plus JIT MSA kernel builds and graph capture outlast the default. | ||
| health_check: | ||
| max_attempts: 1440 | ||
| interval_seconds: 5 | ||
| roles: | ||
| agg: | ||
| nodes: 1 | ||
| workers: 1 | ||
| gpus: 4 | ||
| # Serve flags follow the cookbook's B300 cells at | ||
| # https://docs.sglang.io/cookbook/autoregressive/MiniMax/MiniMax-M3.1. | ||
| args: | ||
| served-model-name: MiniMaxAI/MiniMax-M3.1-Flash | ||
| trust-remote-code: true | ||
| reasoning-parser: minimax-m3 | ||
| tool-call-parser: minimax-m3 | ||
| # Seven-token DSpark, the bundled draft's dspark_block_size. Throughput runs | ||
| # switch to synthetic acceptance at the golden acceptance length. | ||
| speculative-algorithm: DSPARK | ||
| speculative-dspark-block-size: 7 | ||
| speculative-use-block-verification: true | ||
| # FP8 draft KV, as vLLM's DSpark drafter uses; bf16 costs ~10 GB of HBM per rank. | ||
| speculative-draft-kv-cache-dtype: fp8_e4m3 | ||
| cuda-graph-backend-prefill: breakable | ||
| tokenizer-worker-num: 8 | ||
| watchdog-timeout: 3600 | ||
| enable-metrics: true | ||
| env: | ||
| PYTHONNOUSERSITE: '1' | ||
| PYTHONUNBUFFERED: '1' | ||
| SGLANG_TIMEOUT_KEEP_ALIVE: '1800' | ||
| FMHA_SM100_ALLOW_JIT: '1' | ||
| benchmark: | ||
| env: | ||
| # Warmup can leave bytes unacknowledged past AIPerf's 30 s default. | ||
| AIPERF_HTTP_TCP_USER_TIMEOUT: '900000' | ||
| AIPERF_REQUIRED_SERVER_METRIC_PREFIX: 'sglang:' | ||
|
|
||
| # Shortest-prefill-first with a decode interval of 32 on TP4 with DRAM KV offload, | ||
| # filling the curve between the TP2 and TP4 points. | ||
| # 2x CONC (AgentX subagent fan-out); the decode graph batch matches it. | ||
| zip_override_tp4_dram_spf_interval32: | ||
| roles: | ||
| agg: | ||
| args: | ||
| tensor-parallel-size: 4 | ||
| moe-runner-backend: flashinfer_trtllm_routed | ||
| chunked-prefill-size: 8192 | ||
| max-running-requests: [40, 88, 104, 120] | ||
| cuda-graph-max-bs-decode: [40, 88, 104, 120] | ||
| mem-fraction-static: 0.90 | ||
| enable-hierarchical-cache: true | ||
| hicache-size: 290 | ||
| hicache-write-policy: write_back | ||
| schedule-policy: shortest-prefill-first | ||
| prefill-decode-interval: 32 | ||
| stream-interval: 20 | ||
| benchmark: | ||
| env: | ||
| CONC: ['20', '44', '52', '60'] | ||
| KV_OFFLOADING: dram | ||
| TOTAL_CPU_DRAM_GB: '1199' | ||
|
|
||
| # At conc 16 the working set fits in HBM; host offload only adds overhead. | ||
| override_tp4_c16_spf_interval32: | ||
| roles: | ||
| agg: | ||
| args: | ||
| tensor-parallel-size: 4 | ||
| moe-runner-backend: flashinfer_trtllm_routed | ||
| chunked-prefill-size: 8192 | ||
| max-running-requests: 32 | ||
| cuda-graph-max-bs-decode: 32 | ||
| mem-fraction-static: 0.90 | ||
| schedule-policy: shortest-prefill-first | ||
| prefill-decode-interval: 32 | ||
| stream-interval: 20 | ||
| benchmark: | ||
| env: | ||
| CONC: '16' | ||
| KV_OFFLOADING: none | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🟡 nit (optional): The new override header breaks the AGENTS.md comments rule. Its first sentence restates the override's own flags, and "filling the curve between the TP2 and TP4 points" gives a benchmarking motive, not a technical reason. Fix: delete both lines and keep only the technical comment "2x CONC (AgentX subagent fan-out); the decode graph batch matches it." above zip_override_tp4_dram_spf_interval32.
Why this was flagged
AGENTS.md:56 says "No header comments describing a file, topology, config, recipe, override, or section." AGENTS.md:58 allows only technical explanation and says "never restate the code". The new header at agentic-tp4-spf-extra.yaml:53-54 repeats the args just below it (shortest-prefill-first, prefill-decode-interval: 32, tensor-parallel-size: 4, KV_OFFLOADING: dram). It then adds a sweep-plan note about where these points sit on the curve. agentic-tp4-spf.yaml has the same first sentence, but that file is not part of this change and does not make the rule optional. Leaving this in brings a new rule violation into the repo. It does not affect runtime behavior.
Verification: In agentic-tp4-spf-extra.yaml, lines 53-54 sit above zip_override_tp4_dram_spf_interval32. The first line repeats the override's own args. The second line says where the points sit in the sweep plan. It gives no technical reason for any value. AGENTS.md:56 says "No header comments describing a file, topology, config, recipe, override, or section." Nothing breaks at runtime.