compilation is fixed

requirements-common.txt

@@ -5,7 +5,7 @@ requests >= 2.26.0
 tqdm
 blake3
 py-cpuinfo
-transformers >= 4.45.2  # Required for Llama 3.2 and Qwen2-VL.
+transformers >= 4.48.2  # Required for Bamba model and Transformers backend.
 tokenizers >= 0.19.1  # Required for Llama 3.
 protobuf # Required by LlamaTokenizer.
 fastapi >= 0.107.0, < 0.113.0; python_version < '3.9'
@@ -34,6 +34,6 @@ pyyaml
 six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
 setuptools>=74.1.1; python_version > '3.11' # Setuptools is used by triton, we need to ensure a modern version is installed for 3.12+ so that it does not try to import distutils, which was removed in 3.12
 einops # Required for Qwen2-VL.
-compressed-tensors == 0.8.1 # required for compressed-tensors
+compressed-tensors == 0.9.1 # required for compressed-tensors
 depyf==0.18.0 # required for profiling and debugging with compilation config
 cloudpickle # allows pickling lambda functions in model_executor/models/registry.py

requirements-test.txt

@@ -106,9 +106,17 @@ dnspython==2.7.0
 docutils==0.16
     # via awscli
 einops==0.8.0
-    # via -r requirements-test.in
+    # via
+    #   -r requirements-test.in
+    #   encodec
+    #   vector-quantize-pytorch
+    #   vocos
+einx==0.3.0
+    # via vector-quantize-pytorch
 email-validator==2.2.0
     # via pydantic
+encodec==0.1.1
+    # via vocos
 evaluate==0.4.3
     # via lm-eval
 fastparquet==2024.11.0
@@ -125,6 +133,8 @@ filelock==3.16.1
     #   triton
 fonttools==4.54.1
     # via matplotlib
+frozendict==2.4.6
+    # via einx
 frozenlist==1.5.0
     # via
     #   aiohttp
@@ -159,6 +169,7 @@ huggingface-hub==0.26.2
     #   timm
     #   tokenizers
     #   transformers
+    #   vocos
 idna==3.10
     # via
     #   anyio
@@ -261,6 +272,8 @@ numpy==1.26.4
     #   cupy-cuda12x
     #   datasets
     #   decord
+    #   einx
+    #   encodec
     #   evaluate
     #   fastparquet
     #   genai-perf
@@ -283,6 +296,7 @@ numpy==1.26.4
     #   torchvision
     #   transformers
     #   tritonclient
+    #   vocos
 nvidia-cublas-cu12==12.4.5.8
     # via
     #   nvidia-cudnn-cu12
@@ -455,6 +469,7 @@ pyyaml==6.0.2
     #   responses
     #   timm
     #   transformers
+    #   vocos
 ray[adag]==2.40.0
     # via -r requirements-test.in
 redis==5.2.0
@@ -517,6 +532,7 @@ scipy==1.13.1
     #   scikit-learn
     #   sentence-transformers
     #   statsmodels
+    #   vocos
 sentence-transformers==3.2.1
     # via -r requirements-test.in
 sentencepiece==0.2.0
@@ -540,7 +556,9 @@ sqlitedict==2.1.0
 statsmodels==0.14.4
     # via genai-perf
 sympy==1.13.1
-    # via torch
+    # via
+    #   einx
+    #   torch
 tabledata==1.3.3
     # via pytablewriter
 tabulate==0.9.0
@@ -568,12 +586,21 @@ torch==2.5.1
     #   -r requirements-test.in
     #   accelerate
     #   bitsandbytes
+    #   encodec
     #   lm-eval
     #   peft
     #   sentence-transformers
     #   tensorizer
     #   timm
+    #   torchaudio
     #   torchvision
+    #   vector-quantize-pytorch
+    #   vocos
+torchaudio==2.5.1
+    # via
+    #   -r requirements-test.in
+    #   encodec
+    #   vocos
 torchvision==0.20.1
     # via timm
 tqdm==4.66.6
@@ -584,13 +611,15 @@ tqdm==4.66.6
     #   lm-eval
     #   nltk
     #   peft
+    #   pqdm
     #   sentence-transformers
     #   tqdm-multiprocess
     #   transformers
 tqdm-multiprocess==0.0.11
     # via lm-eval
-transformers==4.47.0
+transformers==4.48.2
     # via
+    #   -r requirements-test.in
     #   genai-perf
     #   lm-eval
     #   peft
@@ -615,6 +644,7 @@ typing-extensions==4.12.2
     #   huggingface-hub
     #   librosa
     #   mistral-common
+    #   pqdm
     #   pydantic
     #   pydantic-core
     #   torch
@@ -626,6 +656,10 @@ urllib3==2.2.3
     #   requests
     #   responses
     #   tritonclient
+vector-quantize-pytorch==1.21.2
+    # via -r requirements-test.in
+vocos==0.1.0
+    # via -r requirements-test.in
 word2number==1.1
     # via lm-eval
 xxhash==3.5.0

vllm/v1/worker/tpu_model_runner.py

@@ -766,11 +766,6 @@ class TPUModelRunner(ModelRunnerBase):
         logger.info("    -- Compilation for decode done in %.2f [secs].",
                     end - start)
 
-    def _initialize_kv_cache(self):
-        kv_cache_spec = self.get_kv_cache_spec()
-
-        kv_cache_config = get_kv_cache_config(vllm_config, kv_cache_spec,
-                                              availble_gpu_memory)
     def initialize_kv_cache(self, kv_cache_config: KVCacheConfig) -> None:
         """
         Initialize KV cache based on `kv_cache_config`.