fix(submit): restore a3c45d3b-proven config + safe improvements

Based on a3c45d3b (last known working docker build):
- yaml: max-num-seqs=2 (fixes t2_n_2), TOPK_SOFTMAX=1 (use prebuilt .so)
- yaml: keep max-model-len=131072, gpu-mem=0.90 (prevents OOM)
- yaml: NO LD_PRELOAD (libcccl not built during docker build)
- xformers: revert to Q-tiling only (flash_attn caused OOM at profiling)
- .dockerignore: exclude all non-essential files from context
- remove libcccl_allocator.so from git tracking

What stays from recent work:
- 14 prebuilt .so (including corex_gdn_chunk_recurrent)
- qwen3_5.py with .float() fix and chunk_recurrent support
- All vendor_overrides and CCCL preload source (for future use)
This commit is contained in:
Claude
2026-08-14 03:35:24 +00:00
parent bce79e44be
commit 67a5639c3c
5 changed files with 58 additions and 76 deletions

View File

@@ -15,7 +15,7 @@ command:
- -tp
- '4'
- --max-num-seqs
- '1'
- '2'
- --disable-log-requests
- --disable-frontend-multiprocessing
- --max-num-batched-tokens