MixtralForCausalLM#
Validated models#
Engine documentation: MixtralForCausalLM in vLLM supported models (architecture MixtralForCausalLM).
Status: Validated with LMCache.
Start the LMCache MP server:
lmcache server --l1-size-gb 100 --eviction-policy LRU
Start vLLM with the LMCache MP connector:
Mixtral-8x7B-v0.1 (4 GPUs):
vllm serve mistralai/Mixtral-8x7B-v0.1 \
--tensor-parallel-size 4 \
--trust-remote-code \
--kv-transfer-config \
'{"kv_connector":"LMCacheMPConnector", "kv_role":"kv_both"}'
Mixtral-8x7B-Instruct-v0.1 (4 GPUs):
vllm serve mistralai/Mixtral-8x7B-Instruct-v0.1 \
--tensor-parallel-size 4 \
--trust-remote-code \
--enable-auto-tool-choice \
--tool-call-parser mistral \
--kv-transfer-config \
'{"kv_connector":"LMCacheMPConnector", "kv_role":"kv_both"}'
Adjust --tensor-parallel-size to match your hardware. For the
generic LMCache + vLLM wiring (ports, remote hosts, in-process mode),
see Quick Start.
Status: Not validated with LMCache.
Status: Not supported. LMCache TRT-LLM integration is in progress.
CacheBlend support#
Compression support#
Method |
Status |
Notes |
|---|---|---|
Not validated |
Caveats#
None known.