MCPcopy
hub / github.com/NVIDIA/TensorRT-LLM / full

Method full

tensorrt_llm/llmapi/utils.py:386–387  ·  view source on GitHub ↗
(self)

Source from the content-addressed store, hash-verified

384 return self._sync_q
385
386 def full(self) -> bool:
387 return len(self._q) == self._q.maxlen
388
389 def empty(self) -> bool:
390 return not self._q

Callers 15

_matmul_ogsFunction · 0.45
_p_matmul_ogsFunction · 0.45
get_topmask_and_fullmaskFunction · 0.45
_swigluFunction · 0.45
ref.pyFile · 0.45
test_gpt_attentionMethod · 0.45
test_plugin_no_cacheMethod · 0.45
_attnMethod · 0.45
test_gpt_attention_smoothquantMethod · 0.45
allcloseMethod · 0.45
test_phiMethod · 0.45
test_llamaMethod · 0.45

Calls

no outgoing calls

Tested by 15

test_gpt_attentionMethod · 0.36
test_plugin_no_cacheMethod · 0.36
_attnMethod · 0.36
test_gpt_attention_smoothquantMethod · 0.36
allcloseMethod · 0.36
test_phiMethod · 0.36
test_llamaMethod · 0.36
test_gpt_float32Method · 0.36
test_gpt_pluginMethod · 0.36
_test_moe_baseMethod · 0.36
load_test_casesMethod · 0.36
setUpMethod · 0.36