Qwen/Qwen3.8-27B served on a Tenstorrent P150x8 (8 Blackhole chips, 8-way tensor parallel) through one vLLM with speculative decoding, lossless for greedy requests: by default a hybrid of the DFlash2 block drafter (1–4 users, contexts up to 12K) and the checkpoint's own MTP head (5–8 users, longer contexts); up to 32 concurrent users, full sampling support, 262K context. Single-user decode ~10 ms/token on natural text (12.5 ms on random tokens) and the fastest long-prompt first token on this hardware (1.1 s at 8K, 2.0 s at 16K, 4.0 s at 32K, 21 s at 131K). The low-concurrency / long-document sibling of the prefill/decode-disaggregated changh95/qwen3.8-27b-pd4x4-p150x8 and the eight-chip…
Independent publisher
Hyunggi Chang
changh95
SLAM nerd goes LLM brr
Models in Library3
Datasets in Library0
Models on Hugging Face35
Followers9
Compare the published evidence
This profile connects the 3 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Image segmentation, Text generation.
Reported licenses: apache-2.0, mit. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Models
This package runs the Motif-3 LLM of Motif Technologies on one Tenstorrent Blackhole Galaxy (32 Blackhole chips). - 53 layers of Grouped Differential Latent Attention (GDLA). - A 4-stream mHC residual. - 384 routed experts and 1 shared expert, all PolyNorm MLPs, with top-8 routing. - 1 MTP (multi-token-prediction) layer. - default: for all traffic. - mtp (opt-in): greedy requests decode up to 1.9× faster with the model's own MTP layer. - Built on tt-metal / ttnn as a plain vLLM model behind the vllm-tt-plugin. - Mesh (4, 8): attention is 8-way tensor-parallel in 4 groups of 8 user lanes; the MoE is 32-way expert-parallel (12 experts per chip). - Decode runs as captured Metal traces. The MTP…
SceneSeg (Autoware VisionPilot): the scene segmentation network of the Autoware Foundation's VisionPilot camera stack, as its scenesegmodel node deployed it, ported to one Tenstorrent Blackhole p150 with tt-nn. One camera image of any size in (converted to BGR8, as the node receives it); the VisionPilot foreground mask (mono8, 255 = foreground, at the input's size) and a 3-class map (background / foreground / road) out, with the node's exact pre- and post-processing. Weights: weights/ of this repo @ a6829b24 (VisionPilot's SceneSegFP32.onnx and its.pth as safetensors, re-hosted from the upstream Google Drive links) · Paper: none (model card AutowareFoundation/SceneSeg) · Autoware package…