Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
11 lines
275 B
Plaintext
11 lines
275 B
Plaintext
#pragma once
|
|
|
|
#include <cstddef>
|
|
#include "cutlass/numeric_types.h"
|
|
|
|
namespace vllm::cutlass_w4a8_utils {
|
|
|
|
bool unified_encode_int4b(cutlass::int4b_t const* in, cutlass::int4b_t* out,
|
|
size_t num_int4_elems);
|
|
|
|
} // namespace vllm::cutlass_w4a8_utils |