Skip to content

docs(qwen35): draft TP2 phased design #450

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.

Sign up for GitHub

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

Open
Mrtroll486 wants to merge 4 commits into
base: main
Choose a base branch
from
Open

docs(qwen35): draft TP2 phased design #450

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f1433c5
docs(qwen35): draft TP2 phased design
Mrtroll486 Jun 24, 2026
aff47fd
doc(qwen35): removed placeholder commands and clarify TP q-gate sharding
Mrtroll486 Jun 24, 2026
e91b6f9
docs(qwen35): tighten TP design around degree-parametric contract
Mrtroll486 Jun 25, 2026
a05b2bc
docs(qwen35): clarify TP phase 1 contract
Mrtroll486 Jun 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docs/index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,7 @@ Organized by domain (model line / subsystem / playbook / lesson) instead of by l
| `models/qwen35/model-crate.md` | `openinfer-qwen35-4b` owns Qwen3.5 model/scheduler/recurrent ops/tests/benches; feature-gated behind `qwen35-4b` (Triton AOT is the only Python build dependency); root loads it through `EngineHandle`. Build/check/clippy, root bench sanity check, historical Qwen3.5 e2e, and scheduler e2e records live here. |
| `models/qwen35/kernel-plan.md` | Qwen3.5-4B has a `openinfer_qwen35_4b::kernel_plan()` static descriptor mirroring the qwen3 module — enumerates every prefill/decode/unified op with its Rust call site, backend, and notes, so you can dump the active kernel mix without reading call sites. Pure refactor (issue #256), no kernel behavior change. |
| `models/qwen35/batched-step-tail.md` | Qwen3.5 issue #353 implementation record: final prefill tail is batched, decode/unified sample from batched logits, host full-vocab copies are logprobs-only, HF + scheduler e2e pass, and final serving A/B supports only the first-token/short-output TTFT claim. |
| `models/qwen35/tp-design.md` | Qwen3.5 TP2 design: reuse Qwen3's controller/worker TP runtime; Phase 1 shards full-attn+MLP while replicating linear/GDR, Phase 2 shards linear attention and GDR state using vLLM's Qwen3Next/GDN contract as reference. |

## models / deepseek-v4

Expand Down
Loading