George HotzandGitHub f50d0e0ee0 cloud device [pr] (#6964) ...

* first try at cloud device [pr]

* real separation

* we're free

* clang works

* unhappy with timeout

* better timeouts and free

* unrelated

* use http verbs + add test

* lines + better test

* fix DELETE

* shorter cloud

* split key

* fix sending renderer

* PTXRenderer serialization

* add sessions

* http.client

* minor timeout bump

* fix keep-alive

* inc server timeout

* real fix timeout

* that one too

2024-10-11 12:24:06 +08:00

..

autogen

add qcom dsp runtime (#6112)

2024-09-13 21:01:33 +03:00

graph

move hcq device to runtime [pr] (#6879)

2024-10-04 22:26:50 +08:00

support

add HCQDEV_WAIT_TIMEOUT_MS (#6968)

2024-10-09 19:50:00 +03:00

__init__.py

pylint runtime/ and shape/ (#5044)

2024-06-18 19:48:18 -04:00

ops_amd.py

add HCQDEV_WAIT_TIMEOUT_MS (#6968)

2024-10-09 19:50:00 +03:00

ops_clang.py

clang compiler args (#6505)

2024-09-13 19:22:27 +03:00

ops_cloud.py

cloud device [pr] (#6964)

2024-10-11 12:24:06 +08:00

ops_cuda.py

nv/cuda compilers touchup (#5759)

2024-07-28 00:15:28 +03:00

ops_disk.py

Make self.fd Optional. (#6855)

2024-10-08 13:25:34 +08:00

ops_dsp.py

dsp offset buffer (#6570)

2024-09-17 23:34:21 +08:00

ops_gpu.py

use mv_address in ops_gpu (#6856)

2024-10-02 22:31:51 +03:00

ops_hip.py

amd fix cwsr for gfx11 (#6950)

2024-10-08 17:44:29 +03:00

ops_llvm.py

add cpu objdump to LLVM/CLANG (#4537)

2024-05-11 14:28:44 -07:00

ops_metal.py

get readable error from wait_check (#6965)

2024-10-09 17:28:58 +03:00

ops_npy.py

pylint runtime/ and shape/ (#5044)

2024-06-18 19:48:18 -04:00

ops_nv.py

nv sync on gpu before local update (#6954)

2024-10-08 17:43:58 +03:00

ops_python.py

CLANG fixed ops python [run_process_replay] (#6866)

2024-10-03 20:40:04 +08:00

ops_qcom.py

correct kernargs alignment (#6984)

2024-10-11 00:06:28 +03:00