### What this PR does / why we need it?
| File Path |
| :--- |
| `tests/e2e/singlecard/compile/backend.py` |
| `tests/e2e/singlecard/compile/test_graphex_norm_quant_fusion.py` |
| `tests/e2e/singlecard/compile/test_graphex_qknorm_rope_fusion.py` |
| `tests/e2e/singlecard/compile/test_norm_quant_fusion.py` |
| `tests/e2e/singlecard/model_runner_v2/test_basic.py` |
| `tests/e2e/singlecard/test_aclgraph_accuracy.py` |
| `tests/e2e/singlecard/test_aclgraph_batch_invariant.py` |
| `tests/e2e/singlecard/test_aclgraph_mem.py` |
| `tests/e2e/singlecard/test_async_scheduling.py` |
| `tests/e2e/singlecard/test_auto_fit_max_mode_len.py` |
| `tests/e2e/singlecard/test_batch_invariant.py` |
| `tests/e2e/singlecard/test_camem.py` |
| `tests/e2e/singlecard/test_completion_with_prompt_embeds.py` |
| `tests/e2e/singlecard/test_cpu_offloading.py` |
| `tests/e2e/singlecard/test_guided_decoding.py` |
| `tests/e2e/singlecard/test_ilama_lora.py` |
| `tests/e2e/singlecard/test_llama32_lora.py` |
| `tests/e2e/singlecard/test_models.py` |
| `tests/e2e/singlecard/test_multistream_overlap_shared_expert.py` |
| `tests/e2e/singlecard/test_quantization.py` |
| `tests/e2e/singlecard/test_qwen3_multi_loras.py` |
| `tests/e2e/singlecard/test_sampler.py` |
| `tests/e2e/singlecard/test_vlm.py` |
| `tests/e2e/singlecard/test_xlite.py` |
| `tests/e2e/singlecard/utils.py` |
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.15.0
- vLLM main:
9562912cea
---------
Signed-off-by: MrZ20 <2609716663@qq.com>
This commit is contained in:
@@ -30,9 +30,7 @@ MODELS = ["Qwen/Qwen3-0.6B"]
|
||||
|
||||
def get_prompt_embeds(chat, tokenizer, embedding_layer):
|
||||
"""Convert chat messages to prompt embeddings."""
|
||||
token_ids = tokenizer.apply_chat_template(chat,
|
||||
add_generation_prompt=True,
|
||||
return_tensors='pt')
|
||||
token_ids = tokenizer.apply_chat_template(chat, add_generation_prompt=True, return_tensors="pt")
|
||||
prompt_embeds = embedding_layer(token_ids).squeeze(0)
|
||||
return prompt_embeds
|
||||
|
||||
@@ -53,15 +51,16 @@ def test_mixed_prompt_embeds_and_text(model_name):
|
||||
|
||||
# Run inference with mixed inputs
|
||||
with VllmRunner(
|
||||
model_name,
|
||||
enable_prompt_embeds=True,
|
||||
cudagraph_capture_sizes=[1, 2, 4, 8],
|
||||
model_name,
|
||||
enable_prompt_embeds=True,
|
||||
cudagraph_capture_sizes=[1, 2, 4, 8],
|
||||
) as vllm_runner:
|
||||
# Test prompt embeddings
|
||||
embeds_output = vllm_runner.model.generate({
|
||||
"prompt_embeds":
|
||||
prompt_embeds,
|
||||
})
|
||||
embeds_output = vllm_runner.model.generate(
|
||||
{
|
||||
"prompt_embeds": prompt_embeds,
|
||||
}
|
||||
)
|
||||
|
||||
# Test text prompt
|
||||
text_output = vllm_runner.model.generate(text_prompt)
|
||||
|
||||
Reference in New Issue
Block a user