project_6

dylanyunlong/project_6

Fork 0

Commit Graph

Author	SHA1	Message	Date
Claude	d8d435c7d0	[BASE] cache_engine.py: CCCL temporary_storage layout two-phase KV cache allocation Source: cccl_upstream/cub/cub/detail/temporary_storage.cuh Target: vllm/worker/cache_engine.py CCCL system design applied: - temporary_storage::layout<SlotsCount>: Phase 1 get_size() computes total bytes, Phase 2 map_to_buffer() allocates one blob and aliases into per-slot views - Applied to _allocate_kv_cache: compute total numel for all layers, allocate one contiguous torch.zeros, slice into per-layer views - Reduces cudaMalloc calls from num_attention_layers to 1 - Guarantees cross-layer memory contiguity (better L2 locality) - slot.create_alias<T>() → layer_flat.view(kv_cache_shape)	2026-08-06 04:22:53 +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

Claude

d8d435c7d0

[BASE] cache_engine.py: CCCL temporary_storage layout two-phase KV cache allocation

Source: cccl_upstream/cub/cub/detail/temporary_storage.cuh
Target: vllm/worker/cache_engine.py

CCCL system design applied:
- temporary_storage::layout<SlotsCount>: Phase 1 get_size() computes
  total bytes, Phase 2 map_to_buffer() allocates one blob and aliases
  into per-slot views
- Applied to _allocate_kv_cache: compute total numel for all layers,
  allocate one contiguous torch.zeros, slice into per-layer views
- Reduces cudaMalloc calls from num_attention_layers to 1
- Guarantees cross-layer memory contiguity (better L2 locality)
- slot.create_alias<T>() → layer_flat.view(kv_cache_shape)

2026-08-06 04:22:53 +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