project_6

dylanyunlong/project_6

Fork 0

Commit Graph

Author	SHA1	Message	Date
Claude	34b3a4a617	[BASE] block_table.py: CCCL dispatch_select_if alias_temporaries batch allocation Source: cccl_upstream/cub/cub/device/dispatch/dispatch_select_if.cuh Target: vllm/core/block/block_table.py CCCL system design applied: - dispatch_select_if alias_temporaries: compute all allocation sizes upfront, pack into single blob, then init all at once - streaming_context_t.advance(): batch state changes instead of mutating mid-iteration - Applied to ensure_num_empty_slots: Phase 1 batch-allocate all new blocks, Phase 2 batch-append to BlockList - Separates allocation planning from execution, preventing prev_block chain corruption during multi-block allocation	2026-08-06 04:22:02 +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

34b3a4a617

[BASE] block_table.py: CCCL dispatch_select_if alias_temporaries batch allocation

Source: cccl_upstream/cub/cub/device/dispatch/dispatch_select_if.cuh
Target: vllm/core/block/block_table.py

CCCL system design applied:
- dispatch_select_if alias_temporaries: compute all allocation sizes
  upfront, pack into single blob, then init all at once
- streaming_context_t.advance(): batch state changes instead of
  mutating mid-iteration
- Applied to ensure_num_empty_slots: Phase 1 batch-allocate all
  new blocks, Phase 2 batch-append to BlockList
- Separates allocation planning from execution, preventing
  prev_block chain corruption during multi-block allocation

2026-08-06 04:22:02 +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