[Kernel] Use Murmur3 RNG for Gumbel sampling (#51367)

Signed-off-by: freyfwt <110148731+freyfwt@users.noreply.github.com>
Signed-off-by: freyfwt <freytian1996@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
This commit is contained in:
freyfwt
2026-09-15 23:52:26 -07:00
committed by GitHub
co-authored by Codex mergify[bot] <37929162+mergify[bot]@users.noreply.github.com> Jiangyun Zhu
parent 0f8fa53acf
commit 18553c5c9f
5 changed files with 216 additions and 26 deletions
@@ -45,7 +45,8 @@ async def test_include_reasoning_true_non_streaming(client: openai.AsyncOpenAI):
response = await client.chat.completions.create(
model=MODEL_NAME,
messages=MESSAGES,
max_tokens=200,
max_tokens=512,
temperature=0,
extra_body={"include_reasoning": True},
)
@@ -63,7 +64,8 @@ async def test_include_reasoning_false_non_streaming(client: openai.AsyncOpenAI)
response = await client.chat.completions.create(
model=MODEL_NAME,
messages=MESSAGES,
max_tokens=200,
max_tokens=512,
temperature=0,
extra_body={"include_reasoning": False},
)
@@ -99,7 +101,8 @@ async def test_include_reasoning_true_streaming(client: openai.AsyncOpenAI):
stream = await client.chat.completions.create(
model=MODEL_NAME,
messages=MESSAGES,
max_tokens=200,
max_tokens=512,
temperature=0,
stream=True,
extra_body={"include_reasoning": True},
)
@@ -130,7 +133,8 @@ async def test_include_reasoning_false_streaming(client: openai.AsyncOpenAI):
stream = await client.chat.completions.create(
model=MODEL_NAME,
messages=MESSAGES,
max_tokens=200,
max_tokens=512,
temperature=0,
stream=True,
extra_body={"include_reasoning": False},
)