tqcq air tqcq
0 Followers · 0 Following
  • Joined on 2026-07-07
Repositories
10
 Projects Packages Public Activity Starred Repositories
tqcq released v2.1.0 at gitea/runner 2026-07-21 15:30:53 +08:00
tqcq synced new reference refs/tags/b10075 to ggml-org/llama.cpp from mirror 2026-07-21 11:29:35 +08:00
tqcq synced commits to refs/tags/b10075 at ggml-org/llama.cpp from mirror 2026-07-21 11:29:35 +08:00
tqcq synced commits to refs/heads/master at ggml-org/llama.cpp from mirror 2026-07-21 11:29:35 +08:00
76f46ad29d hexagon: add CLAMP op (#25934)
2beefef688 ui: Sidebar Conversations Bulk Action + Improved Settings logic/UI (#25815)
Compare 2 commits »
tqcq synced commits to refs/heads/master at ggml-org/llama.cpp from mirror 2026-07-21 03:19:33 +08:00
91d2fc3875 llama_dsv4: write only used rows in state (#25325)
4ee6a9af71 ui: fix collapsed user bubble with markdown rendering (#25869)
43b5e63589 UI: fix Settings/Display tool call content toggle (#25783)
1521a9ac31 ui: enable the agentic flow when only the JS sandbox is active (#25865)
Compare 4 commits »
tqcq synced commits to refs/tags/b10069 at ggml-org/llama.cpp from mirror 2026-07-20 19:09:35 +08:00
tqcq synced new reference refs/tags/b10069 to ggml-org/llama.cpp from mirror 2026-07-20 19:09:35 +08:00
tqcq synced commits to refs/heads/master at ggml-org/llama.cpp from mirror 2026-07-20 19:09:35 +08:00
178a6c4493 opencl: Support broadcast for Adreno MUL_MAT and honor view_offs for Adreno Q8_0 MUL_MAT for llama-server multi-stream (#25910)
tqcq created branch add-test in tqcq/manylinux 2026-07-19 20:24:09 +08:00
tqcq pushed to add-test at tqcq/manylinux 2026-07-19 20:24:09 +08:00
tqcq pushed to master at tqcq/manylinux 2026-07-19 10:06:23 +08:00
e63b2ba03b init: manylinux2014 build base image with CMake 3.31.6, gdb, zip
tqcq pushed to master at tqcq/manylinux 2026-07-19 09:55:28 +08:00
42d57b4ebb init: manylinux2014 build base image with CMake 3.31.6, gdb, zip
tqcq synced commits to refs/tags/b10067 at ggml-org/llama.cpp from mirror 2026-07-19 02:24:27 +08:00
tqcq synced new reference refs/tags/b10068 to ggml-org/llama.cpp from mirror 2026-07-19 02:24:27 +08:00
tqcq synced new reference refs/tags/b10067 to ggml-org/llama.cpp from mirror 2026-07-19 02:24:27 +08:00
tqcq synced commits to refs/tags/b10068 at ggml-org/llama.cpp from mirror 2026-07-19 02:24:27 +08:00
tqcq synced commits to refs/heads/master at ggml-org/llama.cpp from mirror 2026-07-19 02:24:27 +08:00
571d0d540d model: rotate injected K/V cache for DFlash (#25823)
4937ca83f4 llama-quant : exclude i32 ffn_gate_tid2eid routing table from quantization (#25787)
Compare 2 commits »
tqcq created branch master in tqcq/manylinux 2026-07-16 17:47:13 +08:00
tqcq pushed to master at tqcq/manylinux 2026-07-16 17:47:13 +08:00
dc9a68f5d8 init: manylinux2014 build base image with CMake 3.31.6, gdb, zip
tqcq created repository tqcq/manylinux 2026-07-15 11:11:13 +08:00