[Mini-VLLM] Cut non-OpenAI surfaces, dead kernels, Mistral stack
- Remove Anthropic, Cohere, SageMaker, decisions, structured-decisions, rl, render-launcher and batch entrypoints; keep scale-out token routes - Drop the Swagger static bundle and the /docs, /redoc routes - Delete device-keyed tuning configs for fused_moe, quant utils, mamba select-state and helion; no sm86 entry ever existed for any of them - Remove ten unused rope variants plus the fbgemm_fp8 and fp_quant quantizers and their config, metrics and loader plumbing - Cut the CPU device build: csrc/cpu, cpu_extension.cmake, cpu requirements and the setup.py cpu target path - Delete 29 environment variables nothing reads and 14 chat-template fallbacks for models this fork no longer registers - Remove nine dead CUDA ops (deepseek_v4, kimi_k3, minimax, muse_spark, dsv3 gemm) with their kernels, bindings, wrappers and CMake entries - Delete the connector test suites that targeted removed connectors - Cut the Mistral tokenizer and parser stack, its tests, and the mistral_common and ijson dependency pins - Restore the Qwen4Exp registry rows and nvidia/mtp.py that an earlier cut deleted while keeping the model tree Co-authored-by: Hinata <hinata@idihore.id> Signed-off-by: MOVZX <movzx@yahoo.com>
This commit is contained in:
@@ -33,7 +33,6 @@ partial-json-parser # used for parsing partial JSON outputs
|
||||
jsonschema >= 4.23.0 # required for MiniMax M3 tool schema validation
|
||||
pyzmq >= 25.0.0
|
||||
msgspec
|
||||
mistral_common[image] >= 1.11.6
|
||||
opencv-python-headless >= 4.13.0 # required for video IO
|
||||
pyyaml
|
||||
six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
|
||||
@@ -47,10 +46,8 @@ python-json-logger # Used by logging as per examples/features/logging_configurat
|
||||
ninja # Required for xgrammar, rocm, tpu, xpu
|
||||
pybase64 # fast base64 implementation
|
||||
cbor2 # Required for cross-language serialization of hashable objects
|
||||
ijson # Required for mistral streaming tool parser
|
||||
setproctitle # Used to set process names for better debugging and monitoring
|
||||
oss-harmony >= 0.0.11 # Required for gpt-oss; includes embedded vocabularies
|
||||
anthropic >= 0.71.0
|
||||
model-hosting-container-standards >= 0.1.14, < 1.0.0
|
||||
mcp >= 2.0.0, < 3.0.0
|
||||
opentelemetry-sdk >= 1.27.0
|
||||
|
||||
@@ -1,29 +0,0 @@
|
||||
# Common dependencies
|
||||
-r common.txt
|
||||
|
||||
setuptools==78.1.1 # this version can reuse CMake build dir; >=78.1.1 for GHSA-5rjg-fvgr-3xxf
|
||||
|
||||
numba == 0.65.0 # Required for N-gram speculative decoding
|
||||
|
||||
# Dependencies for CPUs
|
||||
torch==2.14.0+cpu; platform_machine == "x86_64" or platform_machine == "s390x" or platform_machine == "aarch64"
|
||||
torch==2.14.0; platform_system == "Darwin" or platform_machine == "ppc64le" or platform_machine == "riscv64"
|
||||
|
||||
# required for the image processor of minicpm-o-2_6, this must be updated alongside torch
|
||||
torchaudio; platform_machine != "s390x" and platform_machine != "riscv64"
|
||||
|
||||
# required for the image processor of phi3v, this must be updated alongside torch
|
||||
torchvision; platform_machine != "riscv64"
|
||||
|
||||
# required for the torchcodec video decoding backend
|
||||
torchcodec >= 0.14; platform_machine != "riscv64" and platform_machine != "ppc64le"
|
||||
|
||||
# Intel Extension for PyTorch, only for x86_64 CPUs
|
||||
intel-openmp==2024.2.1; platform_machine == "x86_64"
|
||||
|
||||
# triton-cpu, only for x86_64 CPUs
|
||||
triton @ https://github.com/triton-lang/triton-cpu/releases/download/v3.8.0/triton-3.8.0+cpu-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl ; platform_machine == "x86_64" and python_version == "3.11"
|
||||
triton @ https://github.com/triton-lang/triton-cpu/releases/download/v3.8.0/triton-3.8.0+cpu-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl ; platform_machine == "x86_64" and python_version >= "3.12"
|
||||
|
||||
# Use this to gather CPU info and optimize based on ARM Neoverse cores
|
||||
py-cpuinfo; platform_machine == "aarch64"
|
||||
File diff suppressed because it is too large
Load Diff
@@ -71,8 +71,6 @@ gpt-oss[eval] >= 0.0.7; python_version > '3.11'
|
||||
|
||||
perceptron # required for isaac test
|
||||
kaldi-native-fbank >= 1.18.7 # required for fireredasr2 test
|
||||
cohere_melody>=0.11.1 # required for cohere command reasoning/tool parser tests
|
||||
cohere>=7.0.0 # required for cohere chat v2 api tests (protocol/serving import cohere.types)
|
||||
|
||||
# Newer versions of datasets require torchcoded, that makes the tests fail in CI because of a missing library.
|
||||
# Older versions are in conflict with teerratorch requirements.
|
||||
|
||||
@@ -70,8 +70,6 @@ gpt-oss[eval]>=0.0.7; python_version > '3.11'
|
||||
|
||||
perceptron # required for isaac test
|
||||
kaldi-native-fbank>=1.18.7 # required for fireredasr2 test
|
||||
cohere_melody>=0.11.1 # required for cohere command reasoning/tool parser tests
|
||||
cohere>=7.0.0 # required for cohere chat v2 api tests (protocol/serving import cohere.types)
|
||||
|
||||
# Newer versions of datasets require torchcoded, that makes the tests fail in CI because of a missing library.
|
||||
# Older versions are in conflict with terratorch requirements.
|
||||
|
||||
@@ -59,8 +59,6 @@ opentelemetry-exporter-otlp>=1.26.0
|
||||
opentelemetry-sdk>=1.26.0
|
||||
opentelemetry-semantic-conventions-ai>=0.4.1
|
||||
|
||||
cohere_melody>=0.11.1 # required for cohere command reasoning/tool parser tests
|
||||
cohere>=7.0.0 # required for cohere chat v2 api tests (protocol/serving import cohere.types)
|
||||
|
||||
# Dependabot GHSA floors for transitive test deps (excl. dependabot.yml ignores).
|
||||
urllib3>=2.7.0
|
||||
|
||||
Reference in New Issue
Block a user