-
Notifications
You must be signed in to change notification settings - Fork 864
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'main' into xiezhq-hierarchical
- Loading branch information
Showing
102 changed files
with
24,046 additions
and
124 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
sgl-kernel/3rdparty/tensorrt_llm/* |
Submodule flashinfer
updated
3 files
+27 −0 | csrc/flashinfer_gemm_sm90_ops.cu | |
+65 −66 | flashinfer/gemm.py | |
+5 −1 | include/flashinfer/attention/scheduler.cuh |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,34 @@ | ||
/* | ||
* Copyright (c) 2022-2024, NVIDIA CORPORATION. All rights reserved. | ||
* | ||
* Licensed under the Apache License, Version 2.0 (the "License"); | ||
* you may not use this file except in compliance with the License. | ||
* You may obtain a copy of the License at | ||
* | ||
* http://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, software | ||
* distributed under the License is distributed on an "AS IS" BASIS, | ||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
* See the License for the specific language governing permissions and | ||
* limitations under the License. | ||
*/ | ||
|
||
#include "tensorrt_llm/common/assert.h" | ||
|
||
namespace | ||
{ | ||
|
||
bool initCheckDebug() | ||
{ | ||
auto constexpr kDebugEnabled = "TLLM_DEBUG_MODE"; | ||
auto const debugEnabled = std::getenv(kDebugEnabled); | ||
return debugEnabled && debugEnabled[0] == '1'; | ||
} | ||
} // namespace | ||
|
||
bool DebugConfig::isCheckDebugEnabled() | ||
{ | ||
static bool const debugEnabled = initCheckDebug(); | ||
return debugEnabled; | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,92 @@ | ||
/* | ||
* Copyright (c) 2022-2024, NVIDIA CORPORATION. All rights reserved. | ||
* | ||
* Licensed under the Apache License, Version 2.0 (the "License"); | ||
* you may not use this file except in compliance with the License. | ||
* You may obtain a copy of the License at | ||
* | ||
* http://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, software | ||
* distributed under the License is distributed on an "AS IS" BASIS, | ||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
* See the License for the specific language governing permissions and | ||
* limitations under the License. | ||
*/ | ||
|
||
#pragma once | ||
|
||
#include "tensorrt_llm/common/stringUtils.h" | ||
#include "tensorrt_llm/common/tllmException.h" | ||
|
||
#include <string> | ||
|
||
namespace tensorrt_llm::common | ||
{ | ||
[[noreturn]] inline void throwRuntimeError(char const* const file, int const line, std::string const& info = "") | ||
{ | ||
throw TllmException(file, line, fmtstr("[TensorRT-LLM][ERROR] Assertion failed: %s", info.c_str())); | ||
} | ||
|
||
} // namespace tensorrt_llm::common | ||
|
||
class DebugConfig | ||
{ | ||
public: | ||
static bool isCheckDebugEnabled(); | ||
}; | ||
|
||
#if defined(_WIN32) | ||
#define TLLM_LIKELY(x) (__assume((x) == 1), (x)) | ||
#define TLLM_UNLIKELY(x) (__assume((x) == 0), (x)) | ||
#else | ||
#define TLLM_LIKELY(x) __builtin_expect((x), 1) | ||
#define TLLM_UNLIKELY(x) __builtin_expect((x), 0) | ||
#endif | ||
|
||
#define TLLM_CHECK(val) \ | ||
do \ | ||
{ \ | ||
TLLM_LIKELY(static_cast<bool>(val)) ? ((void) 0) \ | ||
: tensorrt_llm::common::throwRuntimeError(__FILE__, __LINE__, #val); \ | ||
} while (0) | ||
|
||
#define TLLM_CHECK_WITH_INFO(val, info, ...) \ | ||
do \ | ||
{ \ | ||
TLLM_LIKELY(static_cast<bool>(val)) \ | ||
? ((void) 0) \ | ||
: tensorrt_llm::common::throwRuntimeError( \ | ||
__FILE__, __LINE__, tensorrt_llm::common::fmtstr(info, ##__VA_ARGS__)); \ | ||
} while (0) | ||
|
||
#define TLLM_CHECK_DEBUG(val) \ | ||
do \ | ||
{ \ | ||
if (TLLM_UNLIKELY(DebugConfig::isCheckDebugEnabled())) \ | ||
{ \ | ||
TLLM_LIKELY(static_cast<bool>(val)) ? ((void) 0) \ | ||
: tensorrt_llm::common::throwRuntimeError(__FILE__, __LINE__, #val); \ | ||
} \ | ||
} while (0) | ||
|
||
#define TLLM_CHECK_DEBUG_WITH_INFO(val, info, ...) \ | ||
do \ | ||
{ \ | ||
if (TLLM_UNLIKELY(DebugConfig::isCheckDebugEnabled())) \ | ||
{ \ | ||
TLLM_LIKELY(static_cast<bool>(val)) \ | ||
? ((void) 0) \ | ||
: tensorrt_llm::common::throwRuntimeError( \ | ||
__FILE__, __LINE__, tensorrt_llm::common::fmtstr(info, ##__VA_ARGS__)); \ | ||
} \ | ||
} while (0) | ||
|
||
#define TLLM_THROW(...) \ | ||
do \ | ||
{ \ | ||
throw NEW_TLLM_EXCEPTION(__VA_ARGS__); \ | ||
} while (0) | ||
|
||
#define TLLM_WRAP(ex) \ | ||
NEW_TLLM_EXCEPTION("%s: %s", tensorrt_llm::common::TllmException::demangle(typeid(ex).name()).c_str(), ex.what()) |
Oops, something went wrong.