project_6

dylanyunlong/project_6

Fork 0

Commit Graph

Author	SHA1	Message	Date
muh	cf245adff9	[fix/correctness] mamba_cache: safe swap via clone, not in-place fancy indexing CCCL source: catch2_test_device_copy_batched.cu CCCL pattern: DeviceCopy::Batched always uses separate src/dst buffers with shuffled destination offsets. Never does in-place scatter. Bug: _swap_mamba_cache used cache[:, [to,from]] = cache[:, [from,to]] PyTorch advanced indexing assignment has undefined evaluation order when src and dst overlap — this can corrupt DeltaNet conv_state and temporal_state during decode, causing silent numerical errors. Fix: explicit temp = clone(from), copy(to→from), copy(tmp→to). Three CUDA memcpy calls instead of one potentially-racy fancy index. This affects every decode step of every DeltaNet layer (alternating layers in Qwen3.6). Corrupt temporal_state → wrong attention output → garbage text or NaN propagation.	2026-08-06 06:33:26 +00:00
dylanyunlon	ef6abf3dc7	[DEPLOY] Complete submission: baseline + all optimizations Adds ALL files needed for Dockerfile build: - qwen3_6_scripts/ (baseline patches + our optimizations) - vllm/ (full vllm package) - paged_attention_v2_pytorch.py (V2 with single-bmm optimization) - Dockerfile + computility-run.yaml Our optimizations vs baseline: 1. paged_attn.py: pre-gathered context KV (eliminates 194 gather calls), Triton try/fallback, V2 heuristic, threshold 32K→64K 2. paged_attention_v2_pytorch.py: fills NotImplementedError, single-bmm Phase 1 (195 launches → 3) 3. patch_enable_triton.py: HAS_TRITON=True with safety fallback 4. patch_triton_tuning.py: BLOCK=64, NUM_WARPS=4 for BI-V100 5. computility-run.yaml: gpu-memory-utilization 0.9→0.95, max-num-batched-tokens 8192→16384 This repo can now be submitted to dev.modelhub.org.cn as-is.	2026-07-30 16:06:20 +00:00

Author

SHA1

Message

Date

muh

cf245adff9

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

CCCL source: catch2_test_device_copy_batched.cu
CCCL pattern: DeviceCopy::Batched always uses separate src/dst buffers
with shuffled destination offsets. Never does in-place scatter.

Bug: _swap_mamba_cache used cache[:, [to,from]] = cache[:, [from,to]]
PyTorch advanced indexing assignment has undefined evaluation order
when src and dst overlap — this can corrupt DeltaNet conv_state and
temporal_state during decode, causing silent numerical errors.

Fix: explicit temp = clone(from), copy(to→from), copy(tmp→to).
Three CUDA memcpy calls instead of one potentially-racy fancy index.

This affects every decode step of every DeltaNet layer (alternating
layers in Qwen3.6). Corrupt temporal_state → wrong attention output
→ garbage text or NaN propagation.

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

dylanyunlon

ef6abf3dc7

[DEPLOY] Complete submission: baseline + all optimizations

Adds ALL files needed for Dockerfile build:
  - qwen3_6_scripts/ (baseline patches + our optimizations)
  - vllm/ (full vllm package)
  - paged_attention_v2_pytorch.py (V2 with single-bmm optimization)
  - Dockerfile + computility-run.yaml

Our optimizations vs baseline:
  1. paged_attn.py: pre-gathered context KV (eliminates 194 gather calls),
     Triton try/fallback, V2 heuristic, threshold 32K→64K
  2. paged_attention_v2_pytorch.py: fills NotImplementedError,
     single-bmm Phase 1 (195 launches → 3)
  3. patch_enable_triton.py: HAS_TRITON=True with safety fallback
  4. patch_triton_tuning.py: BLOCK=64, NUM_WARPS=4 for BI-V100
  5. computility-run.yaml: gpu-memory-utilization 0.9→0.95,
     max-num-batched-tokens 8192→16384

This repo can now be submitted to dev.modelhub.org.cn as-is.

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

2 Commits