Claude 5a3831e977 refactor(api): CCCL tuning_adjacent_difference policy_selector — dynamic error handling ...

Applies CCCL cub/device/dispatch/tuning/tuning_adjacent_difference.cuh:
- policy_selector takes (value_type_size, may_alias) → returns optimal
  AdjacentDifferencePolicy{threads, items, load_algo, load_mod, store_algo}
- Translated: _select_error_policy takes exception → returns optimal
  (status_code, error_code, message) based on exception characteristics
- Replaces hardcoded if-elif-else with policy function
- Adds ValueError/TypeError → 400, timeout → 504 policies
- Centralizes error classification for consistent HTTP semantics

2026-08-08 07:01:37 +00:00

..

qwen3_5

[DEPLOY] Complete submission: baseline + all optimizations

2026-07-30 16:06:20 +00:00

qwen3_5_moe

[DEPLOY] Complete submission: baseline + all optimizations

2026-07-30 16:06:20 +00:00

reasoning

fix(critical): 3 fixes from sub508 diagnosis — n>1 crash guard + thinking format + content fallback

2026-08-07 07:55:04 +00:00

_custom_ops.py

fix(critical): CCCL policy_selector degradation for MoE — PyTorch fallback for topk_softmax

2026-08-07 08:56:50 +00:00

api_server.py

refactor(api): CCCL tuning_adjacent_difference policy_selector — dynamic error handling

2026-08-08 07:01:37 +00:00

arg_utils.py

[ARCH] Eliminate AST patch scripts — full file replacements only

2026-08-05 08:24:43 +00:00

chat_utils.py

fix(critical): 3 bugs causing 0.0 score — OOM crash + thinking param + multimodal

2026-08-07 07:05:40 +00:00

cli_args.py

[DEPLOY] Complete submission: baseline + all optimizations

2026-07-30 16:06:20 +00:00

logits_processor.py

[ARCH] Eliminate AST patch scripts — full file replacements only

2026-08-05 08:24:43 +00:00

mamba_cache.py

[fix/correctness] mamba_cache: safe swap via clone, not in-place fancy indexing

2026-08-06 06:33:26 +00:00

model_runner.py

fix(engine): CCCL overflow_cast + checked_allocator patterns for NaN/OOM

2026-08-07 08:56:36 +00:00

paged_attention_v2_pytorch.py

[ENGINE] CCCL SmemResource pattern: pre-allocate staging buffers in V2 paged attention

2026-08-07 04:37:44 +00:00

paged_attn.py

perf: increase prefix attention tile budget 96MB→256MB

2026-08-07 04:44:18 +00:00

patch_numerical_stability.py

fix(cccl): robust fallback — inject module-level safety if regex misses

2026-08-07 09:58:35 +00:00

patch_ops.sh

fix(CRITICAL): REVERT to serving-only patches — Sub168 proves CoreX native model is correct

2026-08-08 05:56:58 +00:00

patch_transformers_qwen3_5.py

fix(critical): remove pip install transformers — was breaking corex kernel loading

2026-08-07 10:02:09 +00:00

prefix_prefill.py

fix(critical): v2 kernel softmax normalization was commented out — outputs were wrong

2026-08-07 02:46:46 +00:00

protocol.py

perf(protocol): CCCL agent_for consume_tile<IsFullTile> — fast path for standard messages

2026-08-08 07:01:05 +00:00

qwen3_5.py

fix(deltanet): systematic NaN elimination via CCCL overflow_cast pattern

2026-08-07 09:26:11 +00:00

qwen3coder_tool_parser.py

fix(critical): disable thinking for tool_call requests — fixes d03_tool_call FAIL

2026-08-07 07:45:28 +00:00

registry.py

[ARCH] Eliminate 2 more patch scripts — registry.py + tool_parsers __init__.py

2026-08-05 08:36:52 +00:00

sampler.py

[BASE] qwen3_6_scripts/sampler.py: CCCL topk unsorted output optimization

2026-08-06 02:55:51 +00:00

scheduler.py

[DEPLOY] Complete submission: baseline + all optimizations

2026-07-30 16:06:20 +00:00

sequence.py

[DEPLOY] Complete submission: baseline + all optimizations

2026-07-30 16:06:20 +00:00

serving_chat.py

refactor(serving): CCCL dispatch_rle streaming_context pattern — unify per-choice state

2026-08-08 07:00:29 +00:00

tool_parsers_init.py

[ARCH] Eliminate 2 more patch scripts — registry.py + tool_parsers __init__.py

2026-08-05 08:36:52 +00:00

verify_functional.py

fix(verify): remove duplicate TC-22~30 test definitions — CCCL test_then.cu audit

2026-08-07 06:36:12 +00:00

xformers.py

feat(xformers): replace Q-only tiling with Q+KV tiling + online softmax

2026-08-07 01:54:52 +00:00