biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[misc] hide best_of from engine (#9261)

Browse Source 
Co-authored-by: Brendan Wong <bjwpokemon@gmail.com>
This commit is contained in:
youkaichao
2024-10-10 21:30:44 -07:00
committed by GitHub
parent 94bf9ae4e9
commit cbc2ef5529
14 changed files with 46 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/entrypoints/openai/test_metrics.py
View File

@@ -70,7 +70,6 @@ EXPECTED_VALUES = {
[("_sum", _NUM_REQUESTS * _NUM_GENERATION_TOKENS_PER_REQUEST),
("_count", _NUM_REQUESTS)],
"vllm:request_params_n": [("_count", _NUM_REQUESTS)],
"vllm:request_params_best_of": [("_count", _NUM_REQUESTS)],
"vllm:prompt_tokens": [("_total",
_NUM_REQUESTS * _NUM_PROMPT_TOKENS_PER_REQUEST)],
"vllm:generation_tokens":
@@ -151,9 +150,6 @@ EXPECTED_METRICS = [
"vllm:request_params_n_sum",
"vllm:request_params_n_bucket",
"vllm:request_params_n_count",
"vllm:request_params_best_of_sum",
"vllm:request_params_best_of_bucket",
"vllm:request_params_best_of_count",
"vllm:num_preemptions_total",
"vllm:prompt_tokens_total",
"vllm:generation_tokens_total",

1
tests/metrics/test_metrics.py
View File

@@ -326,7 +326,6 @@ def assert_metrics(engine: LLMEngine, disable_log_stats: bool,
"vllm:e2e_request_latency_seconds",
"vllm:request_prompt_tokens",
"vllm:request_generation_tokens",
"vllm:request_params_best_of",
"vllm:request_params_n",
]
for metric_name in request_histogram_metrics:

4
tests/tracing/test_tracing.py
View File

@@ -98,8 +98,6 @@ def test_traces(trace_service):
SpanAttributes.LLM_REQUEST_TOP_P) == sampling_params.top_p
assert attributes.get(
SpanAttributes.LLM_REQUEST_MAX_TOKENS) == sampling_params.max_tokens
assert attributes.get(
SpanAttributes.LLM_REQUEST_BEST_OF) == sampling_params.best_of
assert attributes.get(SpanAttributes.LLM_REQUEST_N) == sampling_params.n
assert attributes.get(SpanAttributes.LLM_USAGE_PROMPT_TOKENS) == len(
outputs[0].prompt_token_ids)
@@ -155,8 +153,6 @@ def test_traces_with_detailed_steps(trace_service):
SpanAttributes.LLM_REQUEST_TOP_P) == sampling_params.top_p
assert attributes.get(
SpanAttributes.LLM_REQUEST_MAX_TOKENS) == sampling_params.max_tokens
assert attributes.get(
SpanAttributes.LLM_REQUEST_BEST_OF) == sampling_params.best_of
assert attributes.get(SpanAttributes.LLM_REQUEST_N) == sampling_params.n
assert attributes.get(SpanAttributes.LLM_USAGE_PROMPT_TOKENS) == len(
outputs[0].prompt_token_ids)