Skip to content

Pull requests: youssofal/MTPLX

New pull request New
37 Open 138 Closed
37 Open 138 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

feat(dashboard): add runtime systems view
#365 opened Aug 26, 2026 by PhilipJohnBasile Contributor Loading…
feat(dashboard): add native operations tab
#364 opened Aug 26, 2026 by PhilipJohnBasile Contributor Loading…
feat(replay): add capture plan orchestration
#363 opened Aug 26, 2026 by PhilipJohnBasile Contributor Loading…
feat(server): add runtime systems status registry
#362 opened Aug 26, 2026 by PhilipJohnBasile Contributor Loading…
feat(policy): add bounded lifecycle hook bus
#361 opened Aug 26, 2026 by PhilipJohnBasile Contributor Loading…
feat(memory): add safe-point SessionBank budget governor
#357 opened Aug 26, 2026 by PhilipJohnBasile Contributor Loading…
capture: make request records privacy-safe by default
#356 opened Aug 26, 2026 by PhilipJohnBasile Contributor Loading…
feat(runtime): add opt-in expert locality telemetry
#355 opened Aug 26, 2026 by PhilipJohnBasile Contributor Loading…
feat(observability): add bounded OTLP HTTP exporter
#354 opened Aug 26, 2026 by PhilipJohnBasile Contributor Loading…
feat(memory): add atomic unified budget coordinator
#353 opened Aug 26, 2026 by PhilipJohnBasile Contributor Loading…
feat(moe): add bounded expert warm-set controller
#352 opened Aug 26, 2026 by PhilipJohnBasile Contributor Loading…
feat(replay): add deterministic counterfactual core
#351 opened Aug 26, 2026 by PhilipJohnBasile Contributor Loading…
feat(cache): add exact semantic session anchors
#350 opened Aug 26, 2026 by PhilipJohnBasile Contributor Loading…
feat(qwen38): add opt-in adaptive depth for native MTP
#347 opened Aug 26, 2026 by davidtai Contributor • Draft
1
perf: int4 simdgroup-mma lanes (small-M vocab + prefill retile), optional native MPP path
#345 opened Aug 25, 2026 by Manojbhat09 Loading…
1
Dense batched MTP: continuous batching, up to n=32, and prefix caching
#338 opened Aug 24, 2026 by grantoverton Loading…
1
Opt-in FR-Spec reduced-vocabulary draft LM head
#317 opened Aug 21, 2026 by grzracz Loading…
1
Port and optimize Mia/Sero/RTX6K DeepSeek V4 Flash DSpark K5 for Metal
#312 opened Aug 21, 2026 by davidtai Contributor Loading…
Add first-class Qwen3.8 DFlash2 backend
#309 opened Aug 21, 2026 by Deviad Loading…
1
1
Qwen3.8 DFlash2 benchmark against Optimized Speed and Quality MTP
#304 opened Aug 20, 2026 by davidtai Contributor Loading…
3
Make the 6-bit hexpack route at m == 4 opt-in: measured as a loss on a real 27B trunk
#302 opened Aug 20, 2026 by Blakeolson21 Loading…
1
Hold the background warmup ladder while a request is in flight
#300 opened Aug 20, 2026 by Blakeolson21 Loading…
1
fix(smart-fan): stop a wedged request pinning fans at max
#295 opened Aug 19, 2026 by El-Patronum Loading…
1
feat(app): add Simplified Chinese localization
#289 opened Aug 18, 2026 by Chendeqisky Loading…
1
perf(mtp): combine greedy token and confidence reads (+0.65% throughput)
#288 opened Aug 18, 2026 by ArthurOstapenko Loading…
2
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.