[Doc][2/N] Reorganize Models and Usage sections (#11755)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
@@ -430,7 +430,7 @@ class ROCmFlashAttentionImpl(AttentionImpl):
|
||||
Returns:
|
||||
shape = [num_tokens, num_heads * head_size]
|
||||
"""
|
||||
# Reminder: Please update docs/source/usage/compatibility_matrix.md
|
||||
# Reminder: Please update docs/source/features/compatibility_matrix.md
|
||||
# If the feature combo become valid
|
||||
if attn_type != AttentionType.DECODER:
|
||||
raise NotImplementedError("Encoder self-attention and "
|
||||
|
||||
+3
-3
@@ -644,7 +644,7 @@ class ModelConfig:
|
||||
self.use_async_output_proc = False
|
||||
return
|
||||
|
||||
# Reminder: Please update docs/source/usage/compatibility_matrix.md
|
||||
# Reminder: Please update docs/source/features/compatibility_matrix.md
|
||||
# If the feature combo become valid
|
||||
from vllm.platforms import current_platform
|
||||
if not current_platform.is_async_output_supported(self.enforce_eager):
|
||||
@@ -665,7 +665,7 @@ class ModelConfig:
|
||||
if self.runner_type == "pooling":
|
||||
self.use_async_output_proc = False
|
||||
|
||||
# Reminder: Please update docs/source/usage/compatibility_matrix.md
|
||||
# Reminder: Please update docs/source/features/compatibility_matrix.md
|
||||
# If the feature combo become valid
|
||||
if speculative_config:
|
||||
logger.warning("Async output processing is not supported with"
|
||||
@@ -2064,7 +2064,7 @@ class LoRAConfig:
|
||||
model_config.quantization)
|
||||
|
||||
def verify_with_scheduler_config(self, scheduler_config: SchedulerConfig):
|
||||
# Reminder: Please update docs/source/usage/compatibility_matrix.md
|
||||
# Reminder: Please update docs/source/features/compatibility_matrix.md
|
||||
# If the feature combo become valid
|
||||
if scheduler_config.chunked_prefill_enabled:
|
||||
logger.warning("LoRA with chunked prefill is still experimental "
|
||||
|
||||
@@ -1148,7 +1148,7 @@ class EngineArgs:
|
||||
disable_logprobs=self.disable_logprobs_during_spec_decoding,
|
||||
)
|
||||
|
||||
# Reminder: Please update docs/source/usage/compatibility_matrix.md
|
||||
# Reminder: Please update docs/source/features/compatibility_matrix.md
|
||||
# If the feature combo become valid
|
||||
if self.num_scheduler_steps > 1:
|
||||
if speculative_config is not None:
|
||||
|
||||
@@ -65,7 +65,7 @@ class MultiStepOutputProcessor(SequenceGroupOutputProcessor):
|
||||
@staticmethod
|
||||
@functools.lru_cache
|
||||
def _log_prompt_logprob_unsupported_warning_once():
|
||||
# Reminder: Please update docs/source/usage/compatibility_matrix.md
|
||||
# Reminder: Please update docs/source/features/compatibility_matrix.md
|
||||
# If the feature combo become valid
|
||||
logger.warning(
|
||||
"Prompt logprob is not supported by multi step workers. "
|
||||
|
||||
@@ -22,7 +22,7 @@ class CPUExecutor(ExecutorBase):
|
||||
|
||||
def _init_executor(self) -> None:
|
||||
assert self.device_config.device_type == "cpu"
|
||||
# Reminder: Please update docs/source/usage/compatibility_matrix.md
|
||||
# Reminder: Please update docs/source/features/compatibility_matrix.md
|
||||
# If the feature combo become valid
|
||||
assert self.lora_config is None, "cpu backend doesn't support LoRA"
|
||||
|
||||
|
||||
@@ -50,7 +50,7 @@ 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/usage/compatibility_matrix.md
|
||||
# Reminder: Please update docs/source/features/compatibility_matrix.md
|
||||
# If the feature combo become valid
|
||||
if not model_config.enforce_eager:
|
||||
logger.warning(
|
||||
|
||||
@@ -108,7 +108,7 @@ def create_spec_worker(*args, **kwargs) -> "SpecDecodeWorker":
|
||||
return spec_decode_worker
|
||||
|
||||
|
||||
# Reminder: Please update docs/source/usage/compatibility_matrix.md
|
||||
# Reminder: Please update docs/source/features/compatibility_matrix.md
|
||||
# If the feature combo become valid
|
||||
class SpecDecodeWorker(LoraNotSupportedWorkerBase):
|
||||
"""Worker which implements speculative decoding.
|
||||
|
||||
+1
-1
@@ -58,7 +58,7 @@ logger = init_logger(__name__)
|
||||
|
||||
# Exception strings for non-implemented encoder/decoder scenarios
|
||||
|
||||
# Reminder: Please update docs/source/usage/compatibility_matrix.md
|
||||
# Reminder: Please update docs/source/features/compatibility_matrix.md
|
||||
# If the feature combo become valid
|
||||
|
||||
STR_NOT_IMPL_ENC_DEC_SWA = \
|
||||
|
||||
@@ -822,7 +822,7 @@ def _pythonize_sampler_output(
|
||||
|
||||
for sgdx, (seq_group,
|
||||
sample_result) in enumerate(zip(seq_groups, samples_list)):
|
||||
# Reminder: Please update docs/source/usage/compatibility_matrix.md
|
||||
# Reminder: Please update docs/source/features/compatibility_matrix.md
|
||||
# If the feature combo become valid
|
||||
# (Check for Guided Decoding)
|
||||
if seq_group.sampling_params.logits_processors:
|
||||
|
||||
@@ -13,7 +13,7 @@ def assert_enc_dec_mr_supported_scenario(
|
||||
a supported scenario.
|
||||
'''
|
||||
|
||||
# Reminder: Please update docs/source/usage/compatibility_matrix.md
|
||||
# Reminder: Please update docs/source/features/compatibility_matrix.md
|
||||
# If the feature combo become valid
|
||||
|
||||
if enc_dec_mr.cache_config.enable_prefix_caching:
|
||||
|
||||
Reference in New Issue
Block a user