DarkSharpness d112f6a25b [Feature] Support JIT set kv cache (#16273)

2026-01-10 17:34:09 -08:00

..

benchmark

[Feature] Support JIT set kv cache (#16273)

2026-01-10 17:34:09 -08:00

csrc

[Feature] Support JIT set kv cache (#16273)

2026-01-10 17:34:09 -08:00

include/sgl_kernel

[jit kernel] support dtype as a cpp template parameter (#16452)

2026-01-08 13:54:33 +08:00

tests

[Feature] Support JIT set kv cache (#16273)

2026-01-10 17:34:09 -08:00

__main__.py

[Minor] Enhance JIT kernel and add dev docs (#14570)

2025-12-23 22:34:59 +08:00

.clang-format

[Feature] HiCache JIT kernel (once again) (#13764)

2025-11-22 22:19:16 -08:00

add_constant.py

[Minor] Enhance JIT kernel and add dev docs (#14570)

2025-12-23 22:34:59 +08:00

cuda_wait_value.py

Add cuda event based on waiting value (#14214)

2025-12-01 18:51:44 +08:00

hicache.py

[bug fix] fix hicache jit kernel (#15177)

2025-12-24 10:31:21 +08:00

kvcache.py

[Feature] Support JIT set kv cache (#16273)

2026-01-10 17:34:09 -08:00

norm.py

[Feature] Support JIT set kv cache (#16273)

2026-01-10 17:34:09 -08:00

per_tensor_quant_fp8.py

[JIT kernel] Apply jit per_tensor_quant_fp8 kernel (#15836)

2026-01-05 10:15:00 +08:00

utils.py

[jit kernel] support dtype as a cpp template parameter (#16452)

2026-01-08 13:54:33 +08:00