thoughtworks
/

MiniMax-M2.5-Eagle3

Text Generation

speculative-decoding

Mixture of Experts

mixture-of-experts

text-generation-inference

Model card Files Files and versions

lujangusface commited on 5 days ago

Commit

fb4699b

·

verified ·

1 Parent(s): 29cdd29

Upload README.md with huggingface_hub

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -128,16 +128,16 @@ EAGLE3 trains a single-layer draft head that predicts the next token using hidde
 *Config: steps=3, topk=4, draft_tokens=8. 8x H200 (TP=4).*
-**With draft_tokens=6 (standard config, verified 2026-04-12)**:
 | Dataset | Baseline (tok/s) | EAGLE3 (tok/s) | Speedup |
 |---------|-----------------|----------------|---------|
-| HumanEval | 109.6 | 158.0 | **1.44x** |
-| Terminal-Bench | 108.9 | 150.2 | **1.38x** |
-| MT-Bench | 109.0 | 143.6 | **1.32x** |
-| SWEBench-Verified | 109.1 | 116.5 | **1.07x** |
-*Config: steps=3, topk=4, draft_tokens=6. 4x H200 (TP=4). Server-side Prometheus metrics.*
 ## Model Architecture

 *Config: steps=3, topk=4, draft_tokens=8. 8x H200 (TP=4).*
+**With draft_tokens=6 (verified 2026-04-12)**:
 | Dataset | Baseline (tok/s) | EAGLE3 (tok/s) | Speedup |
 |---------|-----------------|----------------|---------|
+| HumanEval | 109.6 | 177.0 | **1.61x** |
+| Terminal-Bench | 108.9 | 160.8 | **1.48x** |
+| MT-Bench | 109.0 | 146.8 | **1.35x** |
+| SWEBench-Verified | 109.1 | 123.1 | **1.13x** |
+*Config: steps=3, topk=4, draft_tokens=8. 4x H200 (TP=4). Server-side Prometheus metrics.*
 ## Model Architecture