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 11, 23:45 UTC
[Misc] Rename CohereForAI references to CohereLabs (#30147)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Russell Bryant committed
Dec 5, 2025 at 14:41 UTC
3633035a3fdee20cca8a8deb72490dc9cacea0f8
6 files changed
+9
-9
docs/models/supported_models.md
+1
-1
@@ -666,7 +666,7 @@ These models primarily accept the [`LLM.generate`](./generative_models.md#llmgen
666
| Architecture | Models | Inputs | Example HF Models | [LoRA](../features/lora.md) | [PP](../serving/parallelism_scaling.md) |
667
|--------------|--------|--------|-------------------|----------------------|---------------------------|
668
| `AriaForConditionalGeneration` | Aria | T + I<sup>+</sup> | `rhymes-ai/Aria` | | |
669
-| `AyaVisionForConditionalGeneration` | Aya Vision | T + I<sup>+</sup> | `CohereForAI/aya-vision-8b`, `CohereForAI/aya-vision-32b`, etc. | | ✅︎ |
669
+| `AyaVisionForConditionalGeneration` | Aya Vision | T + I<sup>+</sup> | `CohereLabs/aya-vision-8b`, `CohereLabs/aya-vision-32b`, etc. | | ✅︎ |
670
| `BeeForConditionalGeneration` | Bee-8B | T + I<sup>E+</sup> | `Open-Bee/Bee-8B-RL`, `Open-Bee/Bee-8B-SFT` | | ✅︎ |
671
| `Blip2ForConditionalGeneration` | BLIP-2 | T + I<sup>E</sup> | `Salesforce/blip2-opt-2.7b`, `Salesforce/blip2-opt-6.7b`, etc. | | ✅︎ |
672
| `ChameleonForConditionalGeneration` | Chameleon | T + I | `facebook/chameleon-7b`, etc. | | ✅︎ |
examples/offline_inference/vision_language.py
+1
-1
@@ -72,7 +72,7 @@ def run_aria(questions: list[str], modality: str) -> ModelRequestData:
72
# Aya Vision
73
def run_aya_vision(questions: list[str], modality: str) -> ModelRequestData:
74
assert modality == "image"
75
- model_name = "CohereForAI/aya-vision-8b"
75
+ model_name = "CohereLabs/aya-vision-8b"
76
77
engine_args = EngineArgs(
78
model=model_name,
examples/offline_inference/vision_language_multi_image.py
+1
-1
@@ -76,7 +76,7 @@ def load_aria(question: str, image_urls: list[str]) -> ModelRequestData:
76
77
78
def load_aya_vision(question: str, image_urls: list[str]) -> ModelRequestData:
79
- model_name = "CohereForAI/aya-vision-8b"
79
+ model_name = "CohereLabs/aya-vision-8b"
80
81
engine_args = EngineArgs(
82
model=model_name,
tests/distributed/test_pipeline_parallel.py
+1
-1
@@ -109,7 +109,7 @@ TEXT_GENERATION_MODELS = {
109
"baichuan-inc/Baichuan2-13B-Chat": PPTestSettings.fast(),
110
"bigscience/bloomz-1b1": PPTestSettings.fast(),
111
"zai-org/chatglm3-6b": PPTestSettings.fast(),
112
- "CohereForAI/c4ai-command-r-v01": PPTestSettings.fast(load_format="dummy"),
112
+ "CohereLabs/c4ai-command-r-v01": PPTestSettings.fast(load_format="dummy"),
113
"databricks/dbrx-instruct": PPTestSettings.fast(load_format="dummy"),
114
"Deci/DeciLM-7B-instruct": PPTestSettings.fast(),
115
"deepseek-ai/deepseek-llm-7b-chat": PPTestSettings.fast(),
tests/models/multimodal/generation/test_common.py
+2
-2
@@ -278,7 +278,7 @@ VLM_TEST_SETTINGS = {
278
marks=[large_gpu_mark(min_gb=64)],
279
),
280
"aya_vision": VLMTestInfo(
281
- models=["CohereForAI/aya-vision-8b"],
281
+ models=["CohereLabs/aya-vision-8b"],
282
test_type=(VLMTestType.IMAGE),
283
prompt_formatter=lambda img_prompt: f"<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{img_prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>", # noqa: E501
284
single_image_prompts=IMAGE_ASSETS.prompts(
@@ -294,7 +294,7 @@ VLM_TEST_SETTINGS = {
294
vllm_runner_kwargs={"mm_processor_kwargs": {"crop_to_patches": True}},
295
),
296
"aya_vision-multi_image": VLMTestInfo(
297
- models=["CohereForAI/aya-vision-8b"],
297
+ models=["CohereLabs/aya-vision-8b"],
298
test_type=(VLMTestType.MULTI_IMAGE),
299
prompt_formatter=lambda img_prompt: f"<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{img_prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>", # noqa: E501
300
single_image_prompts=IMAGE_ASSETS.prompts(
tests/models/registry.py
+3
-3
@@ -211,10 +211,10 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
211
trust_remote_code=True,
212
),
213
"CohereForCausalLM": _HfExamplesInfo(
214
- "CohereForAI/c4ai-command-r-v01", trust_remote_code=True
214
+ "CohereLabs/c4ai-command-r-v01", trust_remote_code=True
215
),
216
"Cohere2ForCausalLM": _HfExamplesInfo(
217
- "CohereForAI/c4ai-command-r7b-12-2024",
217
+ "CohereLabs/c4ai-command-r7b-12-2024",
218
trust_remote_code=True,
219
),
220
"CwmForCausalLM": _HfExamplesInfo("facebook/cwm", min_transformers_version="4.58"),
@@ -581,7 +581,7 @@ _AUTOMATIC_CONVERTED_MODELS = {
581
_MULTIMODAL_EXAMPLE_MODELS = {
582
# [Decoder-only]
583
"AriaForConditionalGeneration": _HfExamplesInfo("rhymes-ai/Aria"),
584
- "AyaVisionForConditionalGeneration": _HfExamplesInfo("CohereForAI/aya-vision-8b"),
584
+ "AyaVisionForConditionalGeneration": _HfExamplesInfo("CohereLabs/aya-vision-8b"),
585
"BeeForConditionalGeneration": _HfExamplesInfo(
586
"Open-Bee/Bee-8B-RL",
587
trust_remote_code=True,