[docs] Start ues CLAUDE rules.
This commit is contained in:
26
.claude/rules/commands.md
Normal file
26
.claude/rules/commands.md
Normal file
@@ -0,0 +1,26 @@
|
||||
# Commands
|
||||
|
||||
## Installation
|
||||
|
||||
```bash
|
||||
pip install -e .
|
||||
```
|
||||
|
||||
## Running
|
||||
|
||||
```bash
|
||||
# Run example
|
||||
python example.py
|
||||
|
||||
# Run benchmarks
|
||||
python bench.py # Standard benchmark
|
||||
python bench_offload.py # CPU offload benchmark
|
||||
```
|
||||
|
||||
## Config Defaults
|
||||
|
||||
- `max_num_batched_tokens`: 16384
|
||||
- `max_num_seqs`: 512
|
||||
- `kvcache_block_size`: 256
|
||||
- `gpu_memory_utilization`: 0.9
|
||||
- `enforce_eager`: False (enables CUDA graphs)
|
||||
Reference in New Issue
Block a user