A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 16:00 UTC
Fix some capitalisations in generated examples doc titles (#16094)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Apr 5, 2025 at 14:44 UTC
97ae6d777f7ce2d2054a36b2ddd2f6b81d5f379a
1 file changed
+2
docs/source/generate_examples.py
+2
@@ -17,6 +17,7 @@ def fix_case(text: str) -> str:
17
"cli": "CLI",
18
"cpu": "CPU",
19
"llm": "LLM",
20
+ "mae": "MAE",
21
"tpu": "TPU",
22
"aqlm": "AQLM",
23
"gguf": "GGUF",
@@ -24,6 +25,7 @@ def fix_case(text: str) -> str:
25
"rlhf": "RLHF",
26
"vllm": "vLLM",
27
"openai": "OpenAI",
28
+ "lmcache": "LMCache",
29
"multilora": "MultiLoRA",
30
"mlpspeculator": "MLPSpeculator",
31
r"fp\d+": lambda x: x.group(0).upper(), # e.g. fp16, fp32