Issues · foundation-model-stack/foundation-model-stack · GitHub

Labels Milestones New issue

Gpt-Oss-20B follow-up - Yarn embeddings in FMS way

#511

· flaviabeo opened

on Mar 3, 2026

Use `search` instead of `match` in `_hf_to_fms_rope()` adapter

#491

· rzbhatti opened

on Nov 21, 2025

Gpt-Oss-20B follow-up - Implement TPMultiheadAttention support

#480

· flaviabeo opened

on Oct 17, 2025

Gpt-Oss-20B follow-up - Add HF equivalency tests

#479

· flaviabeo opened

on Oct 15, 2025

Gpt-Oss-20B follow-up - Model unfuse weights

#478

· flaviabeo opened

on Oct 15, 2025

Gpt-Oss-20B follow-up - Add optmizations to attention and MoE code.

#477

· flaviabeo opened

on Oct 15, 2025

Add support to openai/gpt-oss-20b

#461

· flaviabeo opened

on Aug 20, 2025

Migrate to `pyproject.toml` based packaging of FMS

#450

· rzbhatti opened

on Jul 14, 2025

[serialization] no guarantee that dictionary has `to` or `device`

#443

· kcirred opened

on Jul 7, 2025

Add unit tests for the tekken tokenizer class

#439

· rzbhatti opened

on Jul 2, 2025

Port `mistralai/Mistral-Small-3.1-24B-Instruct-2503` to FMS

#428

· rzbhatti opened

on Jun 23, 2025

Infer GPTQ model from hf model config

#392

· JRosenkranz opened

on Apr 8, 2025