[Doc] Create a new "Usage" section (#10827)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2024-12-05 11:19:35 +08:00
committed by GitHub
parent 8d370e91cb
commit aa39a8e175
25 changed files with 218 additions and 125 deletions
+1 -1
View File
@@ -430,7 +430,7 @@ class ROCmFlashAttentionImpl(AttentionImpl):
Returns:
shape = [num_tokens, num_heads * head_size]
"""
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
if attn_type != AttentionType.DECODER:
raise NotImplementedError("Encoder self-attention and "
+4 -4
View File
@@ -509,7 +509,7 @@ class ModelConfig:
self.use_async_output_proc = False
return
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
if device_config.device_type not in ("cuda", "tpu", "xpu", "hpu"):
logger.warning(
@@ -525,7 +525,7 @@ class ModelConfig:
self.use_async_output_proc = False
return
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
if device_config.device_type == "cuda" and self.enforce_eager:
logger.warning(
@@ -540,7 +540,7 @@ class ModelConfig:
if self.task == "embedding":
self.use_async_output_proc = False
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
if speculative_config:
logger.warning("Async output processing is not supported with"
@@ -1704,7 +1704,7 @@ class LoRAConfig:
model_config.quantization)
def verify_with_scheduler_config(self, scheduler_config: SchedulerConfig):
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
if scheduler_config.chunked_prefill_enabled:
raise ValueError("LoRA is not supported with chunked prefill yet.")
+1 -1
View File
@@ -1111,7 +1111,7 @@ class EngineArgs:
disable_logprobs=self.disable_logprobs_during_spec_decoding,
)
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
if self.num_scheduler_steps > 1:
if speculative_config is not None:
+1 -1
View File
@@ -65,7 +65,7 @@ class MultiStepOutputProcessor(SequenceGroupOutputProcessor):
@staticmethod
@functools.lru_cache
def _log_prompt_logprob_unsupported_warning_once():
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
logger.warning(
"Prompt logprob is not supported by multi step workers. "
+1 -1
View File
@@ -23,7 +23,7 @@ class CPUExecutor(ExecutorBase):
def _init_executor(self) -> None:
assert self.device_config.device_type == "cpu"
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
assert self.lora_config is None, "cpu backend doesn't support LoRA"
+1 -1
View File
@@ -46,7 +46,7 @@ class CpuPlatform(Platform):
import vllm.envs as envs
from vllm.utils import GiB_bytes
model_config = vllm_config.model_config
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
if not model_config.enforce_eager:
logger.warning(
+1 -1
View File
@@ -104,7 +104,7 @@ def create_spec_worker(*args, **kwargs) -> "SpecDecodeWorker":
return spec_decode_worker
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
class SpecDecodeWorker(LoraNotSupportedWorkerBase):
"""Worker which implements speculative decoding.
+1 -1
View File
@@ -47,7 +47,7 @@ logger = init_logger(__name__)
# Exception strings for non-implemented encoder/decoder scenarios
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
STR_NOT_IMPL_ENC_DEC_SWA = \
+1 -1
View File
@@ -817,7 +817,7 @@ def _pythonize_sampler_output(
for sgdx, (seq_group,
sample_result) in enumerate(zip(seq_groups, samples_list)):
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
# (Check for Guided Decoding)
if seq_group.sampling_params.logits_processors:
+1 -1
View File
@@ -13,7 +13,7 @@ def assert_enc_dec_mr_supported_scenario(
a supported scenario.
'''
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
if enc_dec_mr.cache_config.enable_prefix_caching: