chore(packages): bump pins to current upstream releases

- awg-tool 0.4.0 -> 0.5.0
- awgen 0.1 -> 0.2
- codeaf 0.7.1 -> 0.8.2
- ds4 -> ee7e840 (2026-10-21)
- freebuff 0.2.19 -> 0.2.34
- graphify 0.9.77 -> 0.9.95 (add pyyaml dependency)
- hipengine 0.6.1 -> 0.8.3
- kubernetes-mcp-server 0.0.67 -> 0.0.69 (build with go_1_27)
- kyojin 1.3 -> 1.7.1 (drop obsolete setup.py/pyproject patches, ship
  gr_mix_hip from the package, add ninja runtime dependency)
- marmel -> de3e99c (2026-10-23)
- omniroute 3.8.50 -> 3.8.52
- open-code-review 1.12.12 -> 1.13.3 (build with go_1_27)
- pilotdeck 2026.10.17 -> 2026.10.20
- radar 1.16.2 -> 1.18.0
- traycer 1.4.2 -> 1.5.1

Verified: nix build passes for every bumped package; kyojin.tests.jit
compiles all five JIT kernels.

🤖 Generated with Codebuff
Co-Authored-By: Codebuff <noreply@codebuff.com>

packages/kyojin/check-jit.py

@@ -30,7 +30,7 @@ if "--gpu" in sys.argv:
     lib.hipModuleUnload.argtypes = [ctypes.c_void_p]
 
 for module, function, args in [
-    ("gr_mix_hip", "compile_hsaco", ()),
+    ("exllamav3.modules.gr_fn.gr_mix_hip", "compile_hsaco", ()),
     ("exllamav3.modules.attention_fn.qsa_prefill_hip", "compile_hsaco", ()),
     ("exllamav3.modules.ple_fn.ple_hip", "compile_hsaco", ()),
     ("exllamav3.vendor.fla.hip.gdn_fused_h_hip", "_compile", ("", "gfx1151")),

packages/kyojin/package.nix

@@ -18,13 +18,13 @@ let
   # only supports AMD Strix Halo, so the kernels are built for gfx1151 alone.
   rocmArch = "gfx1151";
 
-  version = "1.3";
+  version = "1.7.1";
 
   src = fetchFromGitHub {
     owner = "Yamz-Labs";
     repo = "kyojin";
     rev = "v${version}";
-    hash = "sha256-/DPoqW/iaLXRAH8XF5RdE+K5YS4jZT6Sic6QeCDQMlU=";
+    hash = "sha256-84lRbN7H5eNG/RG8Ygvo9cByGOVOp7moFi0GS/YF+mU=";
   };
 
   # setup.py passes EXL3_ROCM_DEV_INCLUDE as -I to every translation unit. The
@@ -111,6 +111,7 @@ let
       jinja2
       llguidance
       marisa-trie
+      ninja
       numpy
       pillow
       pydantic
@@ -136,26 +137,9 @@ let
       EXL3_HIP_DEFINES = "EXL3_HIP_STG_PAD";
     };
 
-    # setup.py pulls the extension source list and the arch helper with
-    # `from exllamav3...import ...`, which runs the package __init__ and
-    # therefore exllamav3/ext.py. That module JIT-compiles the extension when no
-    # precompiled exllamav3_ext is importable, i.e. during every wheel build
-    # (and it wants a writable $HOME for it). Register an empty `exllamav3`
-    # package first so only the two leaf modules are imported, and load
-    # build_config without the package wrapper.
-    postPatch = ''
-      sed -i '1i import sys as _sys, types as _types; _exl3_pkg = _types.ModuleType("exllamav3"); _exl3_pkg.__path__ = ["exllamav3"]; _sys.modules.setdefault("exllamav3", _exl3_pkg)' setup.py
-      sed -i 's|^from exllamav3\.exllamav3_ext\.build_config import get_sources as _get_sources$|import sys as _exl3_sys; _exl3_sys.path.insert(0, "exllamav3/exllamav3_ext"); from build_config import get_sources as _get_sources; _exl3_sys.path.pop(0)|' setup.py
-      grep -q 'from build_config import' setup.py
-
-      # Upstream serves these from the checkout (pip install -e .); the wheel only
-      # packages what pyproject lists, and three things are read out of the
-      # installed package at run time: the .hip sources the JIT kernels compile,
-      # the qsa_proof marker gating the QSA prefill kernel, and the dense-GEMM
-      # tuning seed (without it every start re-tunes for ~7 minutes).
-      sed -i 's|^    "exllamav3_ext/\*\*/\*",$|&\n    "**/*.hip",\n    "**/*.ok",\n    "model/dense_gemm_tune_seed.txt",|' pyproject.toml
-      grep -q '"\*\*/\*.hip"' pyproject.toml
-    '';
+    # setup.py loads exllamav3/exllamav3_ext/build_config.py by path (and
+    # pyproject.toml ships the .hip sources, qsa_proof markers, and dense-GEMM
+    # tuning seed), so no source patches are needed.
 
     # tests/ needs a real gfx1151 GPU and the published model packs.
     doCheck = false;
@@ -189,10 +173,7 @@ stdenv.mkDerivation {
   # exllamav3 finds hipcc under $EXL3_ROCM_SDK, and hipclang only finds the
   # amdgcn bitcode through $HIP_DEVICE_LIB_PATH (hipcc's own DEVICE_LIB_PATH is
   # not enough for a --genco call). The ROCm paths stay out of LD_LIBRARY_PATH
-  # (upstream Trap 1/5: a second libhsa segfaults torch), and PYTHONPATH gets
-  # `gr/`: upstream env.sh puts the repo root there so `import gr_mix_hip` (the
-  # hand-written gated-residual WMMA kernel the server asks for with
-  # EXL3_GR_HIP=1) resolves, and it is not part of the wheel either.
+  # (upstream Trap 1/5: a second libhsa segfaults torch).
   dontConfigure = true;
   dontBuild = true;
 
@@ -210,7 +191,6 @@ stdenv.mkDerivation {
         --set HIP_DEVICE_LIB_PATH ${rocmPackages."rocm-device-libs"}/amdgcn/bitcode \
         --set EXL3_EXPANDABLE_SEGMENTS 0 \
         --prefix PATH : ${lib.makeBinPath [ stdenv.cc ]} \
-        --prefix PYTHONPATH : ${src}/gr \
         --add-flags "${src}/tools/$model/serve.py"
     done
 
@@ -229,7 +209,6 @@ stdenv.mkDerivation {
           # matmul; a custom hipcc must select its own bitcode in its subprocess.
           HIP_DEVICE_LIB_PATH = "${rocmPackages."rocm-device-libs"}/amdgcn/bitcode";
           EXL3_EXPANDABLE_SEGMENTS = "0";
-          PYTHONPATH = "${src}/gr";
           KYOJIN_REQUIRE_SDK = lib.boolToString (jitRocmSdk != null);
         }
         ''