arch(CRITICAL): match Sub168 proven engine config exactly
Sub168 scored 60194.6 with these exact params: - max_model_len=100000 (was 256000) - max_num_seqs=1 (was 2 → caused crash cascade) - gpu_memory_utilization=0.9 (was 0.95) - chunked_prefill=disabled (was enabled) - max_num_batched_tokens=default (was 4096) - max_seq_len_to_capture=8192 (was 32768) Root cause of Sub508/509 0-score: engine crash at t2_n_2 with max_num_seqs=2 caused Connection Refused cascade.
This commit is contained in:
@@ -8,16 +8,14 @@ command:
|
|||||||
- --served-model-name
|
- --served-model-name
|
||||||
- llm
|
- llm
|
||||||
- --max-model-len
|
- --max-model-len
|
||||||
- '256000'
|
- '100000'
|
||||||
- --gpu-memory-utilization
|
- --gpu-memory-utilization
|
||||||
- '0.95'
|
- '0.9'
|
||||||
- --trust-remote-code
|
- --trust-remote-code
|
||||||
- -tp
|
- -tp
|
||||||
- '4'
|
- '4'
|
||||||
- --max-num-seqs
|
- --max-num-seqs
|
||||||
- '2'
|
- '1'
|
||||||
- --max-num-batched-tokens
|
|
||||||
- '4096'
|
|
||||||
- --disable-log-requests
|
- --disable-log-requests
|
||||||
- --disable-frontend-multiprocessing
|
- --disable-frontend-multiprocessing
|
||||||
- --enforce-eager
|
- --enforce-eager
|
||||||
@@ -27,9 +25,8 @@ command:
|
|||||||
- --reasoning-parser
|
- --reasoning-parser
|
||||||
- qwen3
|
- qwen3
|
||||||
- --enable-prefix-caching
|
- --enable-prefix-caching
|
||||||
- --enable-chunked-prefill
|
|
||||||
- --max-seq-len-to-capture
|
- --max-seq-len-to-capture
|
||||||
- '32768'
|
- '8192'
|
||||||
- --dtype
|
- --dtype
|
||||||
- half
|
- half
|
||||||
env:
|
env:
|
||||||
|
|||||||
@@ -247,11 +247,11 @@ class OpenAIServingChat(OpenAIServing):
|
|||||||
logger.exception("Error in loading multi-modal data")
|
logger.exception("Error in loading multi-modal data")
|
||||||
return self.create_error_response(str(e))
|
return self.create_error_response(str(e))
|
||||||
|
|
||||||
# Allow n≤2 (matches max_num_seqs=2 in computility-run.yaml).
|
# Allow n≤2: Sub168 passes t2_n_2 with max_num_seqs=1 (vLLM
|
||||||
# Sub168 passes t2_n_2 with HTTP 200. Reject n>2 to prevent OOM.
|
# serializes generation internally). Reject n>2 to prevent OOM.
|
||||||
if request.n is not None and request.n > 2:
|
if request.n is not None and request.n > 2:
|
||||||
logger.warning(
|
logger.warning(
|
||||||
"n=%d rejected with 400 (exceeds max_num_seqs=2)", request.n)
|
"n=%d rejected with 400 (exceeds max supported value)", request.n)
|
||||||
return self.create_error_response(
|
return self.create_error_response(
|
||||||
f"n={request.n} exceeds the maximum supported value of 2.")
|
f"n={request.n} exceeds the maximum supported value of 2.")
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user