Claude
9fda58f7cd
[CRITICAL] computility-run.yaml: add all corex env vars + align with proven job66 config
ROOT CAUSE FIX for deployment crash (job 100 → status=failed):
- libcusolver.so not found because LD_LIBRARY_PATH was missing
- Added all 10 env vars from successful job 66 submission:
VLLM_ATTENTION_BACKEND, ENABLE_CUSTOM_IPC, PYTHONPATH,
LD_LIBRARY_PATH, VLLM_COREX_FA2/GDN/MOE_LIBRARY,
VLLM_REQUEST_METRICS_FILE, VLLM_CACHE_BLOCK_SIZE
- Aligned CLI args: --enforce-eager --dtype half
--max-model-len 256000 --gpu-memory-utilization 0.95
--max-num-seqs 2 --max-num-batched-tokens 4096
Also: xformers.py Q-tiling CCCL agent_sub_warp_merge_sort patterns:
- ShortCircuit: skip tiling loop when q_len <= _Q_CHUNK
- _TempStorage union: pre-allocate qc_q_pos once, reuse via slicing
Source: cccl_upstream/cub/cub/agent/agent_sub_warp_merge_sort.cuh
2026-08-06 04:27:39 +00:00
..
2026-07-30 16:06:20 +00:00
2026-07-30 16:06:20 +00:00
2026-07-30 16:06:20 +00:00
2026-08-05 08:38:40 +00:00
2026-07-30 16:06:20 +00:00
2026-08-05 08:24:43 +00:00
2026-07-30 16:06:20 +00:00
2026-07-30 16:06:20 +00:00
2026-08-05 08:24:43 +00:00
2026-07-30 16:06:20 +00:00
2026-08-06 01:41:49 +00:00
2026-08-06 02:53:07 +00:00
2026-08-05 08:38:40 +00:00
2026-07-30 16:06:20 +00:00
2026-07-30 16:06:20 +00:00
2026-08-06 03:02:29 +00:00
2026-07-30 16:06:20 +00:00
2026-08-05 08:36:52 +00:00
2026-08-06 02:55:51 +00:00
2026-07-30 16:06:20 +00:00
2026-07-30 16:06:20 +00:00
2026-07-30 16:06:20 +00:00
2026-08-05 08:36:52 +00:00
2026-08-06 02:30:48 +00:00
2026-08-06 04:27:39 +00:00