lei_lei a760a7ab4b fix(backends): honor enable_thinking=false in sglang and vllm (#11715) ...

Those backends only forwarded the flag when it was "true", so "false"
never reached apply_chat_template and Qwen3 kept thinking on.

Signed-off-by: lei_lei <96427312+leilei3167@users.noreply.github.com>

2026-08-25 12:52:57 +02:00

..

backend.py

fix(backends): honor enable_thinking=false in sglang and vllm (#11715)

2026-08-25 12:52:57 +02:00

install.sh

fix(backends): repair release CI build/test breaks (kokoros, fish-speech, llama-cpp-quantization, sglang) (#10547)

2026-06-27 09:42:22 +02:00

Makefile

feat(sglang): wire engine_args, add cuda13 build, ship MTP gallery demos (#9686)

2026-05-07 17:27:29 +02:00

package.sh

feat(backends): add sglang (#9359)

2026-04-16 22:40:56 +02:00

requirements-after.txt

feat(backends): add sglang (#9359)

2026-04-16 22:40:56 +02:00

requirements-cpu-after.txt

feat(backends): add sglang (#9359)

2026-04-16 22:40:56 +02:00

requirements-cpu.txt

chore(deps): bump torch CPU wheels to 2.12.1 (#10969)

2026-07-20 08:34:33 +02:00

requirements-cublas12-after.txt

fix(sglang): bound cuda-tile below the 1.6 prereleases (#11320)

2026-08-03 19:00:28 +02:00

requirements-cublas12.txt

feat(sglang): wire engine_args, add cuda13 build, ship MTP gallery demos (#9686)

2026-05-07 17:27:29 +02:00

requirements-cublas13-after.txt

fix(sglang): bound cuda-tile below the 1.6 prereleases (#11320)

2026-08-03 19:00:28 +02:00

requirements-cublas13.txt

feat(sglang): wire engine_args, add cuda13 build, ship MTP gallery demos (#9686)

2026-05-07 17:27:29 +02:00

requirements-hipblas-after.txt

feat(backends): add sglang (#9359)

2026-04-16 22:40:56 +02:00

requirements-hipblas.txt

feat(backends): add sglang (#9359)

2026-04-16 22:40:56 +02:00

requirements-install.txt

feat(backends): add sglang (#9359)

2026-04-16 22:40:56 +02:00

requirements-intel-after.txt

feat(backends): add sglang (#9359)

2026-04-16 22:40:56 +02:00

requirements-intel.txt

feat(backends): add sglang (#9359)

2026-04-16 22:40:56 +02:00

requirements-l4t13-after.txt

fix(sglang): bound cuda-tile below the 1.6 prereleases (#11320)

2026-08-03 19:00:28 +02:00

requirements-l4t13.txt

fix(L4T13 backends): switch vllm/sglang/vllm-omni to PyPI aarch64+cu130 wheels (#9950)

2026-05-22 23:01:22 +02:00

requirements.txt

feat(backends): add sglang (#9359)

2026-04-16 22:40:56 +02:00

run.sh

feat(backends): add sglang (#9359)

2026-04-16 22:40:56 +02:00

test.py

fix(backends): honor enable_thinking=false in sglang and vllm (#11715)

2026-08-25 12:52:57 +02:00

test.sh

feat(sglang): wire engine_args, add cuda13 build, ship MTP gallery demos (#9686)

2026-05-07 17:27:29 +02:00