GitHub - Jimmys-Code/vllm_inference_gemma

Name		Name	Last commit message	Last commit date
Latest commit History 6 Commits
__pycache__		__pycache__
system_prompts		system_prompts
.gitignore		.gitignore
CLAUDE.md		CLAUDE.md
GLM_air.md		GLM_air.md
concurrent_load_test.py		concurrent_load_test.py
gemini.txt		gemini.txt
gemma.txt		gemma.txt
gemma3_gguf_patch.py		gemma3_gguf_patch.py
gemma_11gb		gemma_11gb
generate_system_prompts.py		generate_system_prompts.py
gguf_docs		gguf_docs
grok.txt		grok.txt
gtp5.txt		gtp5.txt
monkey-patch		monkey-patch
probe.py		probe.py
pyproject.toml		pyproject.toml
qwen!!!!!!!!		qwen!!!!!!!!
r.txt		r.txt
realistic_load_test.py		realistic_load_test.py
requirements.lock		requirements.lock
requirements.txt		requirements.txt
shared_system_realistic_load_test.py		shared_system_realistic_load_test.py
single_user_test.py		single_user_test.py
system_prompt_1.txt		system_prompt_1.txt
test_gemma3_gguf.py		test_gemma3_gguf.py
use_vram.py		use_vram.py
vllm_api.py		vllm_api.py