project_6

dylanyunlong/project_6

Fork 0

Commit Graph

Author	SHA1	Message	Date
Claude	c241764506	fix(critical): wrap get_scheduler_config in try-catch — prevent n=2 engine crash cascade Sub508 log: t2_n_2 → HTTP 500 → engine crash → ALL subsequent 24+ tests HTTP 500. The scheduler config call may throw if engine is in a bad state. Wrapping in try-catch ensures we return 400 (not 500) and the engine stays alive.	2026-08-07 07:51:11 +00:00
Claude	c2bca49aa8	fix(serving_chat): shallow copy bug — [[]] * n and [parser] * n share references When n>=2, all_previous_token_ids entries pointed to the SAME list, so appending tokens for choice 0 corrupted choice 1's history. Same for tool_parsers: all choices shared one stateful parser instance. Changed to list comprehensions that create independent objects. Found via CCCL result_policy.cuh read: distributed result delivery requires isolated per-rank state — same principle applies to per-choice token tracking in vLLM streaming.	2026-08-07 07:11:11 +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

c241764506

fix(critical): wrap get_scheduler_config in try-catch — prevent n=2 engine crash cascade

Sub508 log: t2_n_2 → HTTP 500 → engine crash → ALL subsequent 24+ tests HTTP 500.
The scheduler config call may throw if engine is in a bad state. Wrapping in
try-catch ensures we return 400 (not 500) and the engine stays alive.

2026-08-07 07:51:11 +00:00

Claude

c2bca49aa8

fix(serving_chat): shallow copy bug — [[]] * n and [parser] * n share references

When n>=2, all_previous_token_ids entries pointed to the SAME list,
so appending tokens for choice 0 corrupted choice 1's history.
Same for tool_parsers: all choices shared one stateful parser instance.

Changed to list comprehensions that create independent objects.

Found via CCCL result_policy.cuh read: distributed result delivery
requires isolated per-rank state — same principle applies to
per-choice token tracking in vLLM streaming.

2026-08-07 07:11:11 +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

3 Commits