6852a2e267
### What this PR does / why we need it?
LMCache-Ascend is LMCache's solution on the Ascend platform and one of
the KVCache pooling solutions for Ascend. We hope to integrate
LMCache-Ascend into the vLLM-Ascend community as one of the official
KVCache pooling solutions for vLLM-Ascend.
We added a new LMCacheAscendConnector in vLLM-Ascend and registered it.
### Does this PR introduce _any_ user-facing change?
Users can specify the kvconnector using `--kv-transfer-config`, allowing
them to freely choose which kvconnector to use, without any user-facing
change.
### How was this patch tested?
Test by specifying `--kv-transfer-config
'{"kv_connector":"LMCacheAscendConnector","kv_role":"kv_both"}'`
- vLLM version: v0.16.0
- vLLM main:
15d76f74e2
---------
Signed-off-by: chloroethylene <jjysama@gmail.com>
33 lines
509 B
Markdown
33 lines
509 B
Markdown
# Feature Guide
|
|
|
|
This section provides a detailed usage guide of vLLM Ascend features.
|
|
|
|
:::{toctree}
|
|
:caption: Feature Guide
|
|
:maxdepth: 1
|
|
graph_mode
|
|
cpu_binding
|
|
quantization
|
|
sleep_mode
|
|
structured_output
|
|
lora
|
|
eplb_swift_balancer
|
|
netloader
|
|
Multi_Token_Prediction
|
|
dynamic_batch
|
|
epd_disaggregation
|
|
kv_pool
|
|
external_dp
|
|
large_scale_ep
|
|
ucm_deployment
|
|
Fine_grained_TP
|
|
layer_sharding
|
|
speculative_decoding
|
|
context_parallel
|
|
npugraph_ex
|
|
weight_prefetch
|
|
sequence_parallelism
|
|
batch_invariance
|
|
lmcache_ascend_deployment
|
|
:::
|