78fad4e348
### What this PR does / why we need it?
Refactor MLP weight prefetch to consistency with MoE Model's prefetching
in terms of code and usage.
Environments VLLM_ASCEND_ENABLE_PREFETCH_MLP,
VLLM_ASCEND_MLP_DOWN_PREFETCH_SIZE and
VLLM_ASCEND_MLP_GATE_UP_PREFETCH_SIZE is removed, usage as following:
--additional-config '{"weight_prefetch_config": { "enabled": true,
"prefetch_ratio": {"mlp": { "gate_up": 1.0, "down": 1.0} }}}'
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
---------
Signed-off-by: leo-pony <nengjunma@outlook.com>
28 lines
414 B
Markdown
28 lines
414 B
Markdown
# Feature Guide
|
|
|
|
This section provides a detailed usage guide of vLLM Ascend features.
|
|
|
|
:::{toctree}
|
|
:caption: Feature Guide
|
|
:maxdepth: 1
|
|
graph_mode
|
|
quantization
|
|
sleep_mode
|
|
structured_output
|
|
lora
|
|
eplb_swift_balancer
|
|
netloader
|
|
Multi_Token_Prediction
|
|
dynamic_batch
|
|
kv_pool
|
|
external_dp
|
|
large_scale_ep
|
|
ucm_deployment
|
|
Fine_grained_TP
|
|
layer_sharding
|
|
speculative_decoding
|
|
context_parallel
|
|
npugraph_ex
|
|
weight_prefetch
|
|
:::
|