Add vLLM v0.18.1 source tree with KV transfer abort fix
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>
This commit is contained in:
11
third_party/vllm/csrc/quantization/cutlass_w4a8/w4a8_utils.cuh
vendored
Normal file
11
third_party/vllm/csrc/quantization/cutlass_w4a8/w4a8_utils.cuh
vendored
Normal file
@@ -0,0 +1,11 @@
|
||||
#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
|
||||
Reference in New Issue
Block a user