ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-28 10:21:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

RPC: support multiple devices including cpu (#1024)

Browse Source 
* RPC support multiple devices

* rpc : update documentation (#16441)

Update the README file to match the newly added functionality of
exposing multiple devices from a single server.

Co-authored-by: Diego Devesa <slarengh@gmail.com>

# Conflicts:
#	examples/rpc/README.md

* Remove memory settings

* rpc : cache and reuse compute graphs (#15405)

Store the last computed graph and reuse it when possible.
Also do not return response from GRAPH_COMPUTE and assume it always
completes successfully. If this this is not the case, the server closes
the connection. This saves us a network round trip to the server.

* Add -cpu to include cpu backend

---------

Co-authored-by: firecoperana <firecoperana>
Co-authored-by: Radoslav Gerganov <rgerganov@gmail.com>
This commit is contained in:
firecoperana
2025-11-30 11:48:02 -06:00
committed by GitHub
parent 52adcf1e90
commit e89064e657
8 changed files with 734 additions and 381 deletions
Download Patch File Download Diff File Expand all files Collapse all files

68
examples/rpc/README.md
View File

@@ -4,7 +4,7 @@
> This example and the RPC backend are currently in a proof-of-concept development stage. As such, the functionality is fragile and
> insecure. **Never run the RPC server on an open network or in a sensitive environment!**
The `rpc-server` allows running `ggml` backend on a remote host.
The `rpc-server` allows exposing `ggml` devices on a remote host.
The RPC backend communicates with one or several instances of `rpc-server` and offloads computations to them.
This can be used for distributed LLM inference with `llama.cpp` in the following way:
@@ -14,27 +14,34 @@ flowchart TD
rpcb---|TCP|srvb
rpcb-.-|TCP|srvn
subgraph hostn[Host N]
srvn[rpc-server]-.-backend3["Backend (CUDA,Metal,etc.)"]
srvn[rpc-server]<-.->dev4["CUDA0"]
srvn[rpc-server]<-.->dev5["CPU"]
end
subgraph hostb[Host B]
srvb[rpc-server]---backend2["Backend (CUDA,Metal,etc.)"]
srvb[rpc-server]<-->dev3["Metal"]
end
subgraph hosta[Host A]
srva[rpc-server]---backend["Backend (CUDA,Metal,etc.)"]
srva[rpc-server]<-->dev["CUDA0"]
srva[rpc-server]<-->dev2["CUDA1"]
end
subgraph host[Main Host]
ggml[llama.cpp]---rpcb[RPC backend]
local["Local devices"]<-->ggml[llama-cli]
ggml[llama-cli]<-->rpcb[RPC backend]
end
style hostn stroke:#66,stroke-width:2px,stroke-dasharray: 5 5
classDef devcls fill:#5B9BD5
class local,dev,dev2,dev3,dev4,dev5 devcls
```
Each host can run a different backend, e.g. one with CUDA and another with Metal.
You can also run multiple `rpc-server` instances on the same host, each with a different backend.
By default, `rpc-server` exposes all available accelerator devices on the host.
If there are no accelerators, it exposes a single `CPU` device.
## Usage
On each host, build the corresponding backend with `cmake` and add `-DGGML_RPC=ON` to the build options.
For example, to build the CUDA backend with RPC support:
### Remote hosts
On each remote host, build the backends for each accelerator by adding `-DGGML_RPC=ON` to the build options.
For example, to build the `rpc-server` with support for CUDA accelerators:
```bash
mkdir build-rpc-cuda
@@ -43,36 +50,49 @@ cmake .. -DGGML_CUDA=ON -DGGML_RPC=ON
cmake --build . --config Release
```
Then, start the `rpc-server` with the backend:
When started, the `rpc-server` will detect and expose all available `CUDA` devices:
```bash
$ bin/rpc-server -p 50052
create_backend: using CUDA backend
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
$ bin/rpc-server
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA T1200 Laptop GPU, compute capability 7.5, VMM: yes
Starting RPC server on 0.0.0.0:50052
Device 0: NVIDIA GeForce RTX 5090, compute capability 12.0, VMM: yes
Starting RPC server v3.0.0
endpoint : 127.0.0.1:50052
local cache : n/a
Devices:
CUDA0: NVIDIA GeForce RTX 5090 (32109 MiB, 31588 MiB free)
```
When using the CUDA backend, you can specify the device with the `CUDA_VISIBLE_DEVICES` environment variable, e.g.:
You can control the set of exposed CUDA devices with the `CUDA_VISIBLE_DEVICES` environment variable or the `--device` command line option. The following two commands have the same effect:
```bash
$ CUDA_VISIBLE_DEVICES=0 bin/rpc-server -p 50052
$ bin/rpc-server --device CUDA0 -p 50052
```
This way you can run multiple `rpc-server` instances on the same host, each with a different CUDA device.
### Main host
On the main host build `llama.cpp` only with `-DGGML_RPC=ON`:
On the main host build `llama.cpp` with the backends for the local devices and add `-DGGML_RPC=ON` to the build options.
Finally, when running `llama-cli` or `llama-server`, use the `--rpc` option to specify the host and port of each `rpc-server`:
```bash
mkdir build-rpc
cd build-rpc
cmake .. -DGGML_RPC=ON
cmake --build . --config Release
$ llama-cli -hf ggml-org/gemma-3-1b-it-GGUF -ngl 99 --rpc 192.168.88.10:50052,192.168.88.11:50052
```
Finally, use the `--rpc` option to specify the host and port of each `rpc-server`:
By default, llama.cpp distributes model weights and the KV cache across all available devices -- both local and remote -- in proportion to each device's available memory.
You can override this behavior with the `--tensor-split` option and set custom proportions when splitting tensor data across devices.
```bash
$ bin/llama-cli -m ../models/tinyllama-1b/ggml-model-f16.gguf -p "Hello, my name is" --repeat-penalty 1.0 -n 64 --rpc 192.168.88.10:50052,192.168.88.11:50052 -ngl 99
```
By default, the cache is stored in the `$HOME/.cache/llama.cpp/rpc` directory and can be controlled via the `LLAMA_CACHE` environment variable.
### Troubleshooting
Use the `GGML_RPC_DEBUG` environment variable to enable debug messages from `rpc-server`:
```bash
$ GGML_RPC_DEBUG=1 bin/rpc-server
```