Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Temp #16

Merged
merged 30 commits into from
Nov 8, 2024
Merged

Temp #16

Changes from 1 commit
Commits
Show all changes
30 commits
Select commit Hold shift + click to select a range
e2292aa
metal : fix minor string leaks (ggml/1004)
pminev Nov 1, 2024
284e5b0
cmake : make it possible linking ggml as external lib (ggml/1003)
ykhrustalev Nov 2, 2024
ce027ad
sync : ggml
ggerganov Nov 4, 2024
329ed91
CANN: adjust backend registry refactor. (#10158)
leo-pony Nov 4, 2024
f8e5813
metal : move dequantize templates to beginning of MSL source (#0)
ggerganov Nov 4, 2024
05697f6
metal : simplify f16 and f32 dequant kernels (#0)
ggerganov Nov 4, 2024
ea02c75
cuda : clear error after changing peer access (#10153)
slaren Nov 4, 2024
6a066b9
fix build break on arm64 linux (#10166)
snadampal Nov 4, 2024
9e0ecfb
server : clarify /slots endpoint, add is_processing (#10162)
ngxson Nov 4, 2024
401558b
ggml : fix q4xx mat mul, increase ggml_aligned_malloc alignment (#10167)
slaren Nov 4, 2024
d5a409e
ggml : fix gelu tables initialization (#10172)
slaren Nov 4, 2024
3407364
Q6_K AVX improvements (#10118)
netrunnereve Nov 4, 2024
a9e8a9a
ggml : fix arch check in bf16_to_fp32 (#10164)
slaren Nov 4, 2024
b8deef0
llama : add <|tool_call|> formatting to Granite template (#10177)
gabe-l-hart Nov 5, 2024
a1eaf6a
metal : add quantized FA support (#10149)
ggerganov Nov 6, 2024
1dc04b2
ggml : adjust is_first_call init value (#10193)
ggerganov Nov 6, 2024
94d8cb8
metal : fix from ptr buffer name (#10189)
slaren Nov 6, 2024
b11f9ba
server : remove hack for extra parallel slot (#10187)
ggerganov Nov 6, 2024
5c333e0
metal : add BF16 support (#8439)
ggerganov Nov 6, 2024
3bcd40b
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acc…
uniartisan Nov 7, 2024
2319126
fix q4_0_8_8 format for corrupted tokens issue (#10198)
snadampal Nov 7, 2024
5107e8c
DRY: Fixes clone functionality (#10192)
wwoodsTM Nov 7, 2024
60e17ce
Remove identical wte/etw logic for jais (#10203)
fmz Nov 7, 2024
97404c4
ggml : add ggml-cpu.h to the public headers (#10204)
slaren Nov 7, 2024
a2c6fd7
scripts : sync update
ggerganov Nov 7, 2024
3b08828
sync : ggml
ggerganov Nov 7, 2024
eec4d71
scripts : add amx to sync-ggml.sh [no ci]
ggerganov Nov 7, 2024
a71d81c
server : revamp chat UI with vuejs and daisyui (#10175)
ngxson Nov 7, 2024
76c6e7f
server : minor UI fix (#10207)
ngxson Nov 7, 2024
c0d480a
Merge branch 'master' into temp
apicalshark Nov 8, 2024
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
CANN: adjust backend registry refactor. (ggml-org#10158)
remove buffer->iface.get_name that used in cann as it was removed in backend registry refactor PR.
leo-pony authored Nov 4, 2024
commit 329ed914c959c510d076fb06b43eeb3f7b804d6f
1 change: 0 additions & 1 deletion ggml/src/ggml-cann.cpp
Original file line number Diff line number Diff line change
@@ -1227,7 +1227,6 @@ static ggml_backend_buffer_t ggml_backend_cann_host_buffer_type_alloc_buffer(ggm

ggml_backend_buffer_t buffer = ggml_backend_cpu_buffer_from_ptr(hostPtr, size);
buffer->buft = buft;
buffer->iface.get_name = ggml_backend_cann_host_buffer_name;
buffer->iface.free_buffer = ggml_backend_cann_host_buffer_free;

return buffer;