HIP: "parallel": 2 + --layer-split on 2x R9700 exits (code 1) after "captured the batch window over slots 0,1"
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 45/100
- Issue type
- Bug
- Clarity
- Mostly clear
- Activity status
- Active
- Tech stack
- cpp
- Domain
- machine-learning
Research direction
No source files or tests are named. Start by reproducing with the reported HIP setup, "parallel": 2, and layer_split "24", then use the offered debug build or full log to investigate the failure after captured the batch window over slots 0,1. Done means parallel decode with a HIP layer split completes without exiting with code 1.
Written by the indexing model from the issue text.
Description
Setup
- Strata v0.1.39 (6f32ec0) built from source, HIP backend, gfx1201, TheRock ROCm 7.10 wheels, Ubuntu 26.04, kernel 7.0
- 2x Radeon AI PRO R9700 (32 GB), Qwen3.8-Flash-Next IQ3_S
layer_split "24",--trim-stage-weights --mmap-experts, MTP--spec 4— 100% of experts resident in VRAM
What happens
With "parallel": 2, the first time two requests decode together the engine exits with code 1 and no error message. Last log line:
strata verify: captured the batch window over slots 0,1
--batch-groups 2 crashes the same way (last line captured the batch window over slots 0).
What works
- Same box single-lane: ~1,227 tok/s prompt (29K tokens), 52-64 tok/s decode, stable.
"parallel": 2on a single R9700 (no split) — fine."parallel": 2with a layer split on 3x RTX 5070 Ti (CUDA) — fine.
So it looks specific to batch decode + layer split on HIP. Happy to run a debug build or send the full log.
- Dominant language
- C++
- Stars
- 11.6k
- Forks
- 1k
- Avg merge
- 7h 46m
- Merged PRs (30d)
- 30
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from Niko1221/Strata
-
ROCm on Windows ZIPOpen
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
Niko1221/Strata#738 · 1 comment · 1 reaction ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 67/100
Niko1221/Strata#694 · 2 comments · 4 reactions ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
Niko1221/Strata#691 · 2 comments ·
Maintainers usually reply within 1 day
Similar issues
-
enhancement
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
Maintainers usually reply within 1 day
-
iOS: hidden scale bar invalidates its intrinsic content size on every layout pass of MLNMapViewOpen
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
maplibre/maplibre-native#4723 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
HarbourMasters/Shipwright#7320 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
-
Make Catch2 optional when `RDK_BUILD_CPP_TESTS=OFF`Possibly taken @pechersky claimed this today. Openbug
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
Maintainers usually reply within 2 days