Skip to content

Conversation

@ArsenKhanamiryan
Copy link

@ArsenKhanamiryan ArsenKhanamiryan commented Jan 29, 2026

set -euo pipefail
set +H

TS="$(date +%Y%m%d_%H%M%S)"
LOG="/tmp/tg_mac_autopilot_fix_${TS}.log"
TMP="/tmp/tg_mac_autopilot_fix_${TS}"
mkdir -p "$TMP"
exec > >(tee -a "$LOG") 2>&1
trap 'rc=$?; rm -rf "$TMP" >/dev/null 2>&1 || true; echo DONE_RC=$rc; echo LOG=$LOG; tail -n 220 "$LOG" 2>/dev/null || true; exit $rc' EXIT

command -v python3 >/dev/null 2>&1 || { echo FATAL missing_python3; exit 1; }

HOME_DIR="$HOME"
ROOT="$HOME_DIR/codex_autopilot_workspace"
BIN="$HOME_DIR/bin"
VENV="$ROOT/venv"
LOGDIR="$ROOT/logs"
RUNDIR="$ROOT/run"
mkdir -p "$ROOT" "$BIN" "$LOGDIR" "$RUNDIR"

touch "$HOME_DIR/.zshrc" || true
grep -q 'export PATH="$HOME/bin:$PATH"' "$HOME_DIR/.zshrc" 2>/dev/null || echo 'export PATH="$HOME/bin:$PATH"' >> "$HOME_DIR/.zshrc"

NEED_INSTALL="1"
if [ -x "$BIN/tg-autopilot" ]; then
if "$BIN/tg-autopilot" --version 2>/dev/null | grep -q 'tg-autopilot-mac-v2'; then
NEED_INSTALL="0"
fi
fi

if [ "$NEED_INSTALL" = "1" ]; then
[ -d "$VENV" ] || python3 -m venv "$VENV"
"$VENV/bin/python" -m pip install --upgrade pip >/dev/null 2>&1 || true
"$VENV/bin/python" -m pip install fastapi uvicorn psutil >/dev/null 2>&1

cat > "$ROOT/panel_app.py" <<'PY'
import os, subprocess
from fastapi import FastAPI, Request
from fastapi.responses import HTMLResponse, PlainTextResponse

HOME=os.path.expanduser("~")
ROOT=os.path.join(HOME,"codex_autopilot_workspace")

def sh(cmd):
p=subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True)
out=[]
for line in p.stdout:
out.append(line)
rc=p.wait()
return rc,"".join(out)

def exists(cmd):
return subprocess.call(["/bin/bash","-lc",f"command -v {cmd} >/dev/null 2>&1"])==0

def doctor_text():
lines=[]
lines.append(f"OK_PYTHON3={1 if exists('python3') else 0}")
lines.append(f"OK_NODE={1 if exists('node') else 0}")
lines.append(f"OK_NPM={1 if exists('npm') else 0}")
lines.append(f"OK_CODE={1 if exists('code') else 0}")
lines.append(f"OK_CODEX={1 if exists('codex') else 0}")
rc,out=sh(["/bin/bash","-lc","code --list-extensions 2>/dev/null | grep -i '^openai.chatgpt$' || true"])
lines.append(f"OK_VSCODE_EXT_openai.chatgpt={1 if out.strip() else 0}")
return "\n".join(lines)+"\n"

app=FastAPI()

@app.get("/health")
def health():
return {"status":"OK"}

@app.get("/", response_class=HTMLResponse)
def index():
return """<!doctype html><title>TG Autopilot</title>

TG Autopilot Panel (Mac)

Doctor Open Workspace

  <script>
  async function run(cmd){
    document.getElementById('out').textContent='RUN '+cmd+'...';
    let r=await fetch('/api/run',{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify({cmd})});
    let t=await r.text();
    document.getElementById('out').textContent=t;
  }
  </script>"""

@app.post("/api/run")
async def api_run(req: Request):
data=await req.json()
cmd=data.get("cmd","")
if cmd=="doctor":
return PlainTextResponse(doctor_text())
if cmd=="open_workspace":
rc,out=sh(["/bin/bash","-lc",f"code '{ROOT}' >/dev/null 2>&1 || true; echo OK_OPENED={ROOT}"])
return PlainTextResponse(out)
return PlainTextResponse("ERR unknown_cmd\n", status_code=400)
PY

cat > "$BIN/tg-autopilot" <<'PY'
#!/usr/bin/env python3
import os, sys, json, subprocess, socket, time, signal, urllib.request, argparse

VERSION="tg-autopilot-mac-v2"
HOME=os.path.expanduser("~")
ROOT=os.path.join(HOME,"codex_autopilot_workspace")
VENV=os.path.join(ROOT,"venv")
RUN=os.path.join(ROOT,"run")
LOG=os.path.join(ROOT,"logs")
os.makedirs(RUN, exist_ok=True)
os.makedirs(LOG, exist_ok=True)
STATE=os.path.join(RUN,"panel_state.json")

def sh(cmd):
p=subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True)
out=[]
for line in p.stdout:
out.append(line)
rc=p.wait()
return rc,"".join(out)

def exists(cmd):
return subprocess.call(["/bin/bash","-lc",f"command -v {cmd} >/dev/null 2>&1"])==0

def free_port():
for p in range(8890, 8910):
s=socket.socket()
try:
s.bind(("127.0.0.1", p))
s.close()
return p
except OSError:
try: s.close()
except: pass
raise SystemExit("FATAL no_free_port_8890_8909")

def load_state():
if not os.path.exists(STATE):
return {}
try:
with open(STATE,"r") as f:
return json.load(f)
except Exception:
return {}

def save_state(d):
with open(STATE,"w") as f:
json.dump(d,f)

def doctor():
lines=[]
lines.append(f"OK_PYTHON3={1 if exists('python3') else 0}")
lines.append(f"OK_NODE={1 if exists('node') else 0}")
lines.append(f"OK_NPM={1 if exists('npm') else 0}")
lines.append(f"OK_CODE={1 if exists('code') else 0}")
lines.append(f"OK_CODEX={1 if exists('codex') else 0}")
rc,out=sh(["/bin/bash","-lc","code --list-extensions 2>/dev/null | grep -i '^openai.chatgpt$' || true"])
lines.append(f"OK_VSCODE_EXT_openai.chatgpt={1 if out.strip() else 0}")
print("\n".join(lines))

def panel_start():
st=load_state()
pid=st.get("pid")
port=st.get("port")
if pid and port:
try:
os.kill(pid, 0)
print(f"OK_ALREADY_RUNNING url=http://127.0.0.1:{port} pid={pid}")
return
except Exception:
pass
port=free_port()
app=os.path.join(ROOT,"panel_app.py")
if not os.path.exists(app):
raise SystemExit("FATAL missing_panel_app.py")
log=os.path.join(LOG, f"panel_{time.strftime('%Y%m%d_%H%M%S')}.log")
cmd=[os.path.join(VENV,"bin","python"),"-m","uvicorn","panel_app:app","--app-dir",ROOT,"--host","127.0.0.1","--port",str(port)]
p=subprocess.Popen(cmd, stdout=open(log,"a"), stderr=subprocess.STDOUT)
save_state({"pid":p.pid,"port":port,"log":log,"started_at":time.time()})
time.sleep(0.9)
print(f"OK_STARTED url=http://127.0.0.1:{port} pid={p.pid} log={log}")

def panel_stop():
st=load_state()
pid=st.get("pid")
if not pid:
print("OK_NOT_RUNNING")
return
try:
os.kill(pid, signal.SIGTERM)
except Exception:
pass
time.sleep(0.4)
try:
os.kill(pid, 0)
try: os.kill(pid, signal.SIGKILL)
except Exception: pass
except Exception:
pass
print("OK_STOPPED")

def panel_status():
st=load_state()
pid=st.get("pid")
port=st.get("port")
if not pid or not port:
print("STATUS=DOWN")
return
alive=0
try:
os.kill(pid, 0)
alive=1
except Exception:
alive=0
print(f"STATUS={'UP' if alive else 'DOWN'} pid={pid} port={port}")
if st.get("log"):
print(f"LOG={st['log']}")
if alive:
print(f"URL=http://127.0.0.1:{port}")

def panel_health():
st=load_state()
port=st.get("port")
if not port:
print("HEALTH=DOWN")
return
url=f"http://127.0.0.1:{port}/health"
try:
with urllib.request.urlopen(url, timeout=3) as r:
code=r.getcode()
print(f"HEALTH_HTTP={code} URL={url}")
except Exception as e:
print(f"HEALTH_HTTP=000 URL={url} ERR={type(e).name}")

def d_map(subcmd):
if subcmd=="start":
panel_start()
return
if subcmd=="stop":
panel_stop()
return
if subcmd=="status":
panel_status()
return
if subcmd=="health":
panel_health()
return
if subcmd=="heal":
panel_stop()
time.sleep(0.4)
panel_start()
panel_health()
return
raise SystemExit("ERR unknown_D_subcmd")

def main():
ap=argparse.ArgumentParser(add_help=True)
ap.add_argument("--version", action="store_true")
ap.add_argument("cmd", nargs="?")
ap.add_argument("subcmd", nargs="?")
args=ap.parse_args()
if args.version:
print(VERSION)
return
if not args.cmd:
print("usage: tg-autopilot doctor|panel-start|panel-stop|panel-status|D <start|stop|status|health|heal>")
sys.exit(2)
if args.cmd=="doctor":
doctor()
return
if args.cmd=="panel-start":
panel_start()
return
if args.cmd=="panel-stop":
panel_stop()
return
if args.cmd=="panel-status":
panel_status()
return
if args.cmd=="D":
if not args.subcmd:
print("usage: tg-autopilot D <start|stop|status|health|heal>")
sys.exit(2)
d_map(args.subcmd)
return
raise SystemExit("ERR unknown_cmd")

if name=="main":
main()
PY

chmod +x "$BIN/tg-autopilot"
fi

WS="$(pwd)"
mkdir -p "$WS/.vscode"
python3 - <<PY
import json, os
ws=os.getcwd()
p=os.path.join(ws,".vscode","settings.json")
data={}
if os.path.exists(p):
try:
with open(p,"r",encoding="utf-8") as f:
data=json.load(f)
except Exception:
data={}
data["python.defaultInterpreterPath"]=os.path.expanduser("~/codex_autopilot_workspace/venv/bin/python")
with open(p,"w",encoding="utf-8") as f:
json.dump(data,f,indent=2,ensure_ascii=False)
print("OK_VSCODE_SETTINGS", p)
print("OK_PYTHON_DEFAULT", data["python.defaultInterpreterPath"])
PY

"$BIN/tg-autopilot" --version
"$BIN/tg-autopilot" doctor
"$BIN/tg-autopilot" D status
"$BIN/tg-autopilot" D start
"$BIN/tg-autopilot" D health

fs-eire and others added 22 commits July 26, 2025 21:36
- DynamicQuantizeMatMul - handle case where B zero point input is
provided but not constant. (microsoft#25544)
- Refactor plugin EP support (microsoft#25541)
- Remove the python installation steps from
win-qnn-arm64-ci-pipeline.yml (microsoft#25552)
- [EP ABI] Node_GetAttrByName returns ORT_NOT_FOUND with non-existing
attr name (microsoft#25565)
- Fix C/C++ documentation generation (microsoft#25569)
- [build] fix multi-config for VCPKG (microsoft#25585)
…1.23.0 release branch (microsoft#25606)

### Description
Cherry-pick the microsoft#25566 for ORT 1.23
This PR cherry-picks some pipeline changes from the main branch to the
1.23.0 release branch.


- **[build] disable CodeQL for NPM Packaging Pipeline (microsoft#25614)**
- **Refactor Java Test Pipeline (microsoft#25608)**
- **[build] upgrade Node.js for NPM packaging pipeline (microsoft#25568)**

And a WebGPU change:

- **[webgpu] Apply Flash Attention if sliding window exceeds KV cache
length (microsoft#25594)**
)

### Description
<!-- Describe your changes. -->
Move moving weights to memory to the end of Graph::Resolve().
Modify Inject so it copies data into TensorProto according to the C API
docs.

### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
TypeAndShape inference runs as a part of `Resolve()` and it unable to
inspect and load the initializers that point to OrtValues at that time.
We choose to move TensorProto to OrtValue conversion at the end of
`Resolve()`.

References: microsoft#25579

Co-authored-by: Dmitri Smirnov <yuslepukhin@users.noreply.github.com>
…#25659)

Cherry-pick MiGraphX EP fixes from upstream for rel-1.23.0

This PR cherry-picks three critical fixes for the MiGraphX Execution
Provider:

1. Fix compilation after cherry-picking from win-onnxruntime (microsoft#25516)
- Adds ORT_UNUSED_PARAMETER(num_devices) to fix unused parameter warning
   - Corrects struct usage in CreateIExecutionProvider method
   
2. Fix CreateExecutionProviderFactory with correct struct and change
vendor_id (microsoft#25625)
- Updates vendor_id from 0x1002 to 0x9999 to allow DML EP to be default
   - Ensures proper device ordering in provider_policy_context.cc

3. Update OrtEpFactory in MiGraphX EP (microsoft#25567)
   - Adds complete OrtEpFactory infrastructure for auto EP selection
   - Implements all required factory methods with noexcept specifiers
   - Sets ort_version_supported to ORT_API_VERSION
- Enables MiGraphX/AMDGPU EP integration with hardware device detection

These fixes ensure MiGraphX EP builds correctly and integrates properly
with
the ORT execution provider selection framework in the 1.23.0 release.

Cherry-picked commits:
- 87f1499
- 14ca6df  
- 131cf40

---------

Co-authored-by: Artur Wojcik <artur.wojcik@amd.com>
Co-authored-by: Owen Zhang <owen_zzz@hotmail.com>
Co-authored-by: ozhang <ozhang@amd.com>
…5, 25652 (microsoft#25701)

### Description
Cherry-pick the following PRs into the `rel-1.23.0` branch:

- microsoft#25391
- microsoft#25611
- microsoft#25656
- microsoft#25346
- microsoft#25374
- microsoft#25664
- microsoft#25675
- microsoft#25652


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

---------

Co-authored-by: Yulong Wang <7679871+fs-eire@users.noreply.github.com>
Co-authored-by: Ishwar Raut <iraut@nvidia.com>
Co-authored-by: Maximilian Müller <44298237+gedoensmax@users.noreply.github.com>
Co-authored-by: Gaurav Garg <gaugarg@nvidia.com>
Co-authored-by: Scott McKay <skottmckay@gmail.com>
Co-authored-by: Chi Lo <54722500+chilo-ms@users.noreply.github.com>
Co-authored-by: Abhishek Jindal <abjindal@microsoft.com>
Co-authored-by: Dmitri Smirnov <yuslepukhin@users.noreply.github.com>
### Description
Cherry-pick the following PRs into `rel-1.23.0`:
- microsoft#25629
- microsoft#25583



### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

---------

Co-authored-by: Chunye Wang@AMD <Chunye.wang@amd.com>
Co-authored-by: mingyue <mingyue@amd.com>
Co-authored-by: Artur Wojcik <artur.wojcik@amd.com>
Co-authored-by: urpetkov-amd <127323899+urpetkov-amd@users.noreply.github.com>
Co-authored-by: Ted Themistokleous <107195283+TedThemistokleous@users.noreply.github.com>
Co-authored-by: Ted Themistokleous <tedthemistokleous@amd.com>
Co-authored-by: Scott McKay <Scott.McKay@microsoft.com>
### Description
Cherry-picks microsoft#25725 into
the `rel-1.23.0` branch.



### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

Co-authored-by: Ankit Maheshkar <ankit.maheshkar@intel.com>
Co-authored-by: jatinwadhwa921 <110383850+jatinwadhwa921@users.noreply.github.com>
### Description
Cherry-pick the following PRs into the `rel-1.23.0` branch:
- microsoft#25592
- microsoft#25622
- microsoft#25688
- microsoft#25729
- microsoft#25743
- microsoft#25769
- microsoft#25745
- microsoft#25761
- microsoft#25751
- microsoft#25716
- microsoft#25228
- microsoft#25768
- microsoft#25788
- microsoft#25747
- microsoft#25800
- microsoft#25818
- microsoft#25762
- microsoft#25749
- microsoft#25831


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

---------

Co-authored-by: quic-tirupath <quic_tirupath@quicinc.com>
Co-authored-by: quic-calvnguy <quic_calvnguy@quicinc.com>
Co-authored-by: qti-kromero <kromero@qti.qualcomm.com>
Co-authored-by: Jeff Kilpatrick <jkilpatrick@qti.qualcomm.com>
Co-authored-by: Scott McKay <skottmckay@gmail.com>
Co-authored-by: David Fan <30608893+jiafatom@users.noreply.github.com>
Co-authored-by: kuanyul-qti <kuanyul@qti.qualcomm.com>
Co-authored-by: Dmitri Smirnov <yuslepukhin@users.noreply.github.com>
Co-authored-by: Chi Lo <54722500+chilo-ms@users.noreply.github.com>
Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
Co-authored-by: Chunye Wang@AMD <chunywan@amd.com>
Co-authored-by: minfhong-qti <minfhong@qti.qualcomm.com>
Co-authored-by: Vishal Agarwal <vishala@nvidia.com>
Co-authored-by: Maximilian Müller <maximilianm@nvidia.com>
Co-authored-by: Maximilian Müller <44298237+gedoensmax@users.noreply.github.com>
Co-authored-by: Changming Sun <chasun@microsoft.com>
Co-authored-by: adrastogi <aditya.rastogi@microsoft.com>
Co-authored-by: Aditya Rastogi <adityar@ntdev.microsoft.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
- **Relax WeightBiasQuantization constraint for larger QDQ node group
(microsoft#25673)**
- **Add cuda graph implementation for NV TRT RTX EP (microsoft#25787)**
- **python GPU IO Bindings for NVIDIA  (microsoft#25776)**
- **Fixes for DynamicQuantizeMatMul and Attention3D tests (microsoft#25814)**
- **Fix a long standing bug on file memory mapping on windows.
(microsoft#25833)**
- **Add API for precompiled model compatibility check using just the
compat info (microsoft#25841)**
- **Enable ABSL_FLAGS flag registration for onnxruntime_perf_test for
mobile build (microsoft#25849)**
- **Add default constructor to Ort::Status. (microsoft#25860)**
- microsoft#25871
- microsoft#25878
- microsoft#25884
- microsoft#25886
- microsoft#25866
### Description
Cherry-pick the following PRs:
microsoft#25943
microsoft#25937 
microsoft#25917
microsoft#25909
microsoft#25898
microsoft#25897
microsoft#25888
microsoft#25881
microsoft#25830
microsoft#25619
microsoft#25575
microsoft#25572
microsoft#25558
microsoft#25530
microsoft#25474
microsoft#25455
microsoft#25110

Also two dependent PRs for qMoE cpu: 
microsoft#25877
microsoft#25822

---------

Co-authored-by: xiaomsft <136376084+xiaomsft@users.noreply.github.com>
Co-authored-by: Xiaoyan Hu <xiaoh@microsoft.com>
Co-authored-by: Akshay Sonawane <111780983+apsonawane@users.noreply.github.com>
Co-authored-by: Kunal Vaishnavi <kvaishnavi@microsoft.com>
Co-authored-by: Pradeep Sakhamoori <psakhamoori@microsoft.com>
Co-authored-by: mingyue <131847423+mingyueliuh@users.noreply.github.com>
Co-authored-by: Maximilian Müller <44298237+gedoensmax@users.noreply.github.com>
Co-authored-by: Adrian Lizarraga <adlizarraga@microsoft.com>
Co-authored-by: Dmitri Smirnov <yuslepukhin@users.noreply.github.com>
Co-authored-by: Emmanuel <91394589+kobby-kobbs@users.noreply.github.com>
Co-authored-by: Emmanuel Assumang <eassumang@microsoft.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: praneshgo <pranesh.iitp@gmail.com>
Co-authored-by: Hariharan Seshadri <shariharan91@gmail.com>
Co-authored-by: Jing Fang <fajin@microsoft.com>
Co-authored-by: Ishwar Raut <iraut@nvidia.com>
This PR cherry-picks the following PRs to the rel-1.23.0 branch:

* microsoft#25938
* microsoft#25957
* microsoft#25960
* microsoft#25968
* microsoft#25971

---------

Co-authored-by: Dmitri Smirnov <yuslepukhin@users.noreply.github.com>
Co-authored-by: Adrian Lizarraga <adlizarraga@microsoft.com>
Co-authored-by: Hariharan Seshadri <shariharan91@gmail.com>
This PR cherry-picks the following PRs to the release branch:
- microsoft#25988
- microsoft#25991

---------

Co-authored-by: Dmitri Smirnov <yuslepukhin@users.noreply.github.com>
Co-authored-by: umangb-09 <umangb@nvidia.com>
This PR cherry-picks several commits from the main branch to the
rel-1.23.0 release branch as part of the release process.

### Changes included:

*   **Major Refactoring of Azure DevOps Pipelines (microsoft#26008)**
    *   Commit: `2e6d7ccfdff55aaf7b0799d7e28b041e607dce2b`
*   **Disables failing test to unblock Python DML Pipeline (microsoft#26043)**
    *   Commit: `64c8f40d01bf14b3cf7ac4cf8606ad9e0e56feb0`
*   **Pin cmake version in macOS github Actions (microsoft#25998)**
    *   Commit: `148f13cc6b44cae156226cd4e0dcfc154691c5b4`
*   **Bump actions/setup-python from 5 to 6 (microsoft#25979)**
    *   Commit: `97a8d332595c974ad24be133df216565493ffb95`
*   **Remove CACHE_URL settings from Github Actions (microsoft#25989)**
    *   Commit: `e2a0999ba4b224ab90ef7a8768dd4941fcc19b17`
*   **Bump actions/checkout from 4 to 5 (microsoft#25771)**
    *   Commit: `f19215db21f8e1a8fc93090748e455f41076f456`
*   **Bump ruff from 0.12.8 to 0.12.9 (microsoft#25772)**
    *   Commit: `78df404871fa2f3fbbb7f1902f9623787ba8dc86`
*   **Bump ruff from 0.12.4 to 0.12.8 (microsoft#25713)**
    *   Commit: `7204746e709005d2c7294e7a24d63a2df4a1aee8`
*   **Update macOS target version from 13.3 to 13.4 (microsoft#25616)**
    *   Commit: `65bd82564cd31e0acf9139cdd826d08193212c6e`

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Prathik Rao <prathik.rao@gmail.com>
- **Major Refactoring of Azure DevOps Pipelines (microsoft#26008)**
- **Convert QNN x64 pipeline to GH (microsoft#26047)**
- **Upgrade com.diffplug.spotless to 7.2.1 in Java build (microsoft#26051)**
- **Fix Mac Catalyst build options. (microsoft#25970)**
- **Update Podfile.template: update macOS target version from 13.3 to 13.4 (microsoft#25699) **
… (microsoft#26087)

Reduce Python and Nuget GPU package size (microsoft#26002)
[CUDA] Add build flag onnxruntime_USE_FPA_INTB_GEMM (microsoft#25802)
### Description
Cherry-pick the following PRs into the ORT 1.23.1 branch:

- Fix Attention GQA implementation on CPU
- **MANUAL MERGE**: see
microsoft#26057
  - main merge date: Sept 15, 11:33am
  - pr: microsoft#25966
  - commit: d530b29
- Address edge GetMemInfo edge cases
  - main merge date: Sept 16, 10:32am
  - pr: microsoft#26021
  - commit: d251f3a
- Implement new Python APIs
  - main merge date: Sept 17, 11:44am
  - pr: microsoft#25999
  - commit: abc63e8
- MemcpyFromHost and MemcpyToHost support for plugin EPs
- **MERGE CONFLICT** on file
onnxruntime/test/optimizer/transpose_optimizer_test.cc. Conflicts with
microsoft#25689
  - main merge date: Sept 23, 10:42am
  - pr: microsoft#26088
  - commit: 4545732
- [TRT RTX EP] Fix bug for generating the correct subgraph in
GetCapability microsoft#26132
  - main merge date: Sept 23, 8:54pm
  - pr: microsoft#26132
  - commit: 72e56e7


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

---------

Co-authored-by: Dmitri Smirnov <yuslepukhin@users.noreply.github.com>
Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
Co-authored-by: Chi Lo <54722500+chilo-ms@users.noreply.github.com>
### Description
Adds the following commits to the `rel-1.23.1` branch for ORT 1.23.1:


- add session_id_ to LogEvaluationStart/Stop, LogSessionCreationStart
  - main merge date: July 31, 1:05am
  - pr: microsoft#25590
  - commit: e753643
- [build] fix WebAssembly build on macOS/arm64
  - main merge date: Aug 5, 8:07am
  - pr: microsoft#25653
  - commit: 53f152b
- [CPU] MoE Kernel (microsoft#25958)
  - main merge date: Sept 10, 4:54pm
  - pr: microsoft#25958
  - commit: 930e640
- [CPU] Block-wise QMoE kernel for CPU
  - main merge date: Sept 15, 8:32am
  - pr: microsoft#26009
  - commit: 5d17734
- [C#] Implement missing APIs
  - main merge date: Sept 24, 10:50am
  - pr: microsoft#26101
  - commit: 35dcab5
- Regenerate test model with ONNX IR < 12
  - main merge date: Sept 24, 2:50pm
  - pr: microsoft#26149
  - commit: 88f2652
- [CPU] Fix compilation errors because of unused variables
  - main merge date: Sept 25, 1:21pm
  - pr: microsoft#26147
  - commit: 42fcd71
- [EP ABI] Check if nodes specified in GetCapability() have already been
assigned
  - main merge date: Sept 26, 1:24am
  - pr: microsoft#26156
  - commit: 67d3ba0
- [QNN EP] Add dynamic option to set HTP performance mode
  - main merge date: Sept 26, 11:55am
  - pr: microsoft#26135
  - commit: 6cc40fd

---------

Co-authored-by: xieofxie <xieofxie@126.com>
Co-authored-by: hualxie <hualxie@microsoft.com>
Co-authored-by: Yulong Wang <7679871+fs-eire@users.noreply.github.com>
Co-authored-by: Akshay Sonawane <111780983+apsonawane@users.noreply.github.com>
Co-authored-by: Dmitri Smirnov <yuslepukhin@users.noreply.github.com>
Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
Co-authored-by: quic-tirupath <quic_tirupath@quicinc.com>
Co-authored-by: quic-ashwshan <quic_ashwshan@quicinc.com>
Adds the following commits to the release-1.23.2 branch for ORT 1.23.2:

- [TensorRT] Fix DDS output bug during engine update
  - PR: microsoft#26272
  - commit id: 00e85dd
- Fix shape inference failure with in-memory external data
   - PR: microsoft#26263
   - commit id: d955476
- [CUDA] replace 90a-virtual by 90-virtual for forward compatible 
  - PR: microsoft#26230
  - commit id: b58911f
- [QNN-EP] Fix logic flow bug
  - PR: microsoft#26148
  - commit id: b282379
- Internal Dupe of microsoft#25255 - [MLAS] Optimize MlasConv using thread
partition opt
  - PR: microsoft#26103
  - commit id: 7362518
- Update qMoE spec to support block quantization
  - PR: microsoft#25641
  - commit id: 7a8ffa8
- [VitisAI] add new api to VitisAI to save graph as a string
  - PR: microsoft#25602
  - commit id: 3361d72
- [[Build] Lock torch, onnxscript and onnx-ir versions to latest]
  - PR: microsoft#26315
  - commit id: ea69c4d

---------

Co-authored-by: Hariharan Seshadri <shariharan91@gmail.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
Co-authored-by: Yateng Hong <toothache9010@gmail.com>
Co-authored-by: Changming Sun <chasun@microsoft.com>
Co-authored-by: Dmitri Smirnov <dmitrism@microsoft.com>
Co-authored-by: Tianlei Wu <tlwu@microsoft.com>
Co-authored-by: quic-calvnguy <quic_calvnguy@quicinc.com>
Co-authored-by: quic_calvnguy <quic_calvnguy@quic_inc.com>
Co-authored-by: yifei410 <31260809+yifei410@users.noreply.github.com>
Co-authored-by: yifei <y.zhou@xilinx.com>
@microsoft-github-policy-service
Copy link
Contributor

@ArsenKhanamiryan please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.

@microsoft-github-policy-service agree [company="{your company}"]

Options:

  • (default - no company specified) I have sole ownership of intellectual property rights to my Submissions and I am not making Submissions in the course of work for my employer.
@microsoft-github-policy-service agree
  • (when company given) I am making Submissions in the course of work for my employer (or my employer has intellectual property rights in my Submissions by contract or applicable law). I have permission from my employer to make Submissions and enter into this Agreement on behalf of my employer. By signing below, the defined term “You” includes me and my employer.
@microsoft-github-policy-service agree company="Microsoft"
Contributor License Agreement

Contribution License Agreement

This Contribution License Agreement (“Agreement”) is agreed to by the party signing below (“You”),
and conveys certain license rights to Microsoft Corporation and its affiliates (“Microsoft”) for Your
contributions to Microsoft open source projects. This Agreement is effective as of the latest signature
date below.

  1. Definitions.
    “Code” means the computer software code, whether in human-readable or machine-executable form,
    that is delivered by You to Microsoft under this Agreement.
    “Project” means any of the projects owned or managed by Microsoft and offered under a license
    approved by the Open Source Initiative (www.opensource.org).
    “Submit” is the act of uploading, submitting, transmitting, or distributing code or other content to any
    Project, including but not limited to communication on electronic mailing lists, source code control
    systems, and issue tracking systems that are managed by, or on behalf of, the Project for the purpose of
    discussing and improving that Project, but excluding communication that is conspicuously marked or
    otherwise designated in writing by You as “Not a Submission.”
    “Submission” means the Code and any other copyrightable material Submitted by You, including any
    associated comments and documentation.
  2. Your Submission. You must agree to the terms of this Agreement before making a Submission to any
    Project. This Agreement covers any and all Submissions that You, now or in the future (except as
    described in Section 4 below), Submit to any Project.
  3. Originality of Work. You represent that each of Your Submissions is entirely Your original work.
    Should You wish to Submit materials that are not Your original work, You may Submit them separately
    to the Project if You (a) retain all copyright and license information that was in the materials as You
    received them, (b) in the description accompanying Your Submission, include the phrase “Submission
    containing materials of a third party:” followed by the names of the third party and any licenses or other
    restrictions of which You are aware, and (c) follow any other instructions in the Project’s written
    guidelines concerning Submissions.
  4. Your Employer. References to “employer” in this Agreement include Your employer or anyone else
    for whom You are acting in making Your Submission, e.g. as a contractor, vendor, or agent. If Your
    Submission is made in the course of Your work for an employer or Your employer has intellectual
    property rights in Your Submission by contract or applicable law, You must secure permission from Your
    employer to make the Submission before signing this Agreement. In that case, the term “You” in this
    Agreement will refer to You and the employer collectively. If You change employers in the future and
    desire to Submit additional Submissions for the new employer, then You agree to sign a new Agreement
    and secure permission from the new employer before Submitting those Submissions.
  5. Licenses.
  • Copyright License. You grant Microsoft, and those who receive the Submission directly or
    indirectly from Microsoft, a perpetual, worldwide, non-exclusive, royalty-free, irrevocable license in the
    Submission to reproduce, prepare derivative works of, publicly display, publicly perform, and distribute
    the Submission and such derivative works, and to sublicense any or all of the foregoing rights to third
    parties.
  • Patent License. You grant Microsoft, and those who receive the Submission directly or
    indirectly from Microsoft, a perpetual, worldwide, non-exclusive, royalty-free, irrevocable license under
    Your patent claims that are necessarily infringed by the Submission or the combination of the
    Submission with the Project to which it was Submitted to make, have made, use, offer to sell, sell and
    import or otherwise dispose of the Submission alone or with the Project.
  • Other Rights Reserved. Each party reserves all rights not expressly granted in this Agreement.
    No additional licenses or rights whatsoever (including, without limitation, any implied licenses) are
    granted by implication, exhaustion, estoppel or otherwise.
  1. Representations and Warranties. You represent that You are legally entitled to grant the above
    licenses. You represent that each of Your Submissions is entirely Your original work (except as You may
    have disclosed under Section 3). You represent that You have secured permission from Your employer to
    make the Submission in cases where Your Submission is made in the course of Your work for Your
    employer or Your employer has intellectual property rights in Your Submission by contract or applicable
    law. If You are signing this Agreement on behalf of Your employer, You represent and warrant that You
    have the necessary authority to bind the listed employer to the obligations contained in this Agreement.
    You are not expected to provide support for Your Submission, unless You choose to do so. UNLESS
    REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING, AND EXCEPT FOR THE WARRANTIES
    EXPRESSLY STATED IN SECTIONS 3, 4, AND 6, THE SUBMISSION PROVIDED UNDER THIS AGREEMENT IS
    PROVIDED WITHOUT WARRANTY OF ANY KIND, INCLUDING, BUT NOT LIMITED TO, ANY WARRANTY OF
    NONINFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
  2. Notice to Microsoft. You agree to notify Microsoft in writing of any facts or circumstances of which
    You later become aware that would make Your representations in this Agreement inaccurate in any
    respect.
  3. Information about Submissions. You agree that contributions to Projects and information about
    contributions may be maintained indefinitely and disclosed publicly, including Your name and other
    information that You submit with Your Submission.
  4. Governing Law/Jurisdiction. This Agreement is governed by the laws of the State of Washington, and
    the parties consent to exclusive jurisdiction and venue in the federal courts sitting in King County,
    Washington, unless no federal subject matter jurisdiction exists, in which case the parties consent to
    exclusive jurisdiction and venue in the Superior Court of King County, Washington. The parties waive all
    defenses of lack of personal jurisdiction and forum non-conveniens.
  5. Entire Agreement/Assignment. This Agreement is the entire agreement between the parties, and
    supersedes any and all prior agreements, understandings or communications, written or oral, between
    the parties relating to the subject matter hereof. This Agreement may be assigned by Microsoft.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

8 participants