A correctness-first bring-up of Muse Glimmer 30B on a single Tenstorrent p150 card, with paged KV cache, native DFlash speculative decoding and an OpenAI-compatible server.
GitHub · Local & open models· ★ 4
1 build · page 1 of 1
1 build · page 1 of 1
A correctness-first bring-up of Muse Glimmer 30B on a single Tenstorrent p150 card, with paged KV cache, native DFlash speculative decoding and an OpenAI-compatible server.
GitHub · Local & open models· ★ 4
ChatForm
Tgmlabs